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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ूर
    -0.07
    質
    -0.07
     hairy
    -0.06
     एड
    -0.06
    _Res
    -0.06
    Dec
    -0.06
     düğ
    -0.06
     State
    -0.06
    详情
    -0.06
    ा↵
    -0.06
    POSITIVE LOGITS
    atively
    0.07
     west
    0.06
     contrary
    0.06
    abilece
    0.06
    payment
    0.06
     відпов
    0.06
     dictionaryWith
    0.06
    .Accept
    0.06
     laz
    0.06
    FA
    0.06
    Act Density 0.000%

    No Known Activations