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

    Neuronpedia

    INDEX
    Explanations

    key terms related to various types of structured information and their components in different contexts

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

    ending in "-ies", "-als", "-ers", or "-tals"

    np_acts-logits-general · gemini-2.0-flash

    substances, concepts, or entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.62
     Majefty
    -0.59
    <bos>
    -0.56
     ſta
    -0.53
     Houſe
    -0.53
     purpoſe
    -0.51
     cookie
    -0.50
     entity
    -0.50
     houſe
    -0.50
     ſtate
    -0.50
    POSITIVE LOGITS
     neler
    0.74
    mphs
    0.72
     leerlingen
    0.70
    itudes
    0.70
    DCs
    0.69
    dics
    0.69
     SDGs
    0.67
    cists
    0.65
    lators
    0.65
    luents
    0.65
    Act Density 3.538%

    No Known Activations