Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical definitions and concepts related to directed graphical models and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical/logical statements or definitions

    np_acts-logits-general · gemini-2.0-flash

    deemed to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.65
    AccessorTable
    -0.40
    PreferredItem
    -0.36
    StylePriority
    -0.35
     ILogger
    -0.35
     AspNetCore
    -0.35
     limité
    -0.34
     sabido
    -0.34
    Życiorys
    -0.34
    HomeAsUpEnabled
    -0.34
    POSITIVE LOGITS
     considered
    0.81
     считается
    0.78
     deemed
    0.75
     Considered
    0.74
     dikatakan
    0.73
     deem
    0.67
     вважа
    0.65
    considered
    0.63
     deems
    0.63
    deemed
    0.59
    Act Density 0.845%

    No Known Activations