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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ried
    -0.08
     pig
    -0.07
    lö
    -0.07
    垦
    -0.07
    ähr
    -0.07
    ().'
    -0.07
    ಐ
    -0.07
     poisonous
    -0.07
    理赔
    -0.06
     Ezek
    -0.06
    POSITIVE LOGITS
     lượt
    0.08
    -half
    0.07
     anytime
    0.07
    ,left
    0.07
    🔜
    0.07
    ＊
    0.07
    口袋
    0.07
     !==
    0.06
     outbreaks
    0.06
     penny
    0.06
    Act Density 0.014%

    No Known Activations