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

    Neuronpedia

    INDEX
    Explanations

    various mathematical and logical notations or symbols

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

    Superscript or subscript indicators in scientific notation

    np_acts-logits-general · gemini-2.0-flash

    special characters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gens
    -0.47
    ch
    -0.44
    ex
    -0.44
     Prit
    -0.44
    ณะ
    -0.43
    tute
    -0.43
    ej
    -0.42
     tanques
    -0.42
    addGap
    -0.42
    ец
    -0.41
    POSITIVE LOGITS
     myſelf
    0.88
     himſelf
    0.83
     continúas
    0.80
    NUMX
    0.79
    তথ্যসূত্র
    0.78
    ⓘ
    0.74
    Personensuche
    0.74
     themſelves
    0.70
     againſt
    0.70
     becauſe
    0.69
    Act Density 0.446%

    No Known Activations