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

    Neuronpedia

    INDEX
    Explanations

    references to specific time intervals and contextual information related to changes or events

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

    measurements or quantities

    np_acts-logits-general · gemini-2.0-flash

    parameters, thresholds, and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.43
     estatus
    -0.40
     utafitiHapana
    -0.40
    baño
    -0.37
     Di
    -0.36
    brä
    -0.35
    fvar
    -0.35
     fat
    -0.34
     precedenti
    -0.34
    แท
    -0.34
    POSITIVE LOGITS
    WriteTagHelper
    0.89
     насељу
    0.81
     themſelves
    0.79
     himſelf
    0.77
    WarningLevel
    0.76
     myſelf
    0.76
    HtmlAttribute
    0.76
     threshold
    0.75
    AsUp
    0.75
     iſt
    0.75
    Act Density 0.621%

    No Known Activations