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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or paragraph

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

    Code, equations, or formulas

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -1.17
     تضيفلها
    -0.92
    ImageContext
    -0.78
     CreateTagHelper
    -0.77
    .*")]
    -0.77
    bootstrapcdn
    -0.74
    PreferredItem
    -0.74
    Personendaten
    -0.74
     للمعارف
    -0.74
     Audiodateien
    -0.73
    POSITIVE LOGITS
    cambrian
    0.49
    >>();
    0.46
    ͂
    0.45
    ?
    0.45
     apex
    0.44
    cleros
    0.44
    _
    0.43
     gitu
    0.43
    =[]
    0.43
    tslib
    0.42
    Act Density 0.013%

    No Known Activations