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

    Neuronpedia

    INDEX
    Explanations

    corpus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    登録
    -0.07
     Lund
    -0.07
     тан
    -0.07
     nếu
    -0.07
    .Fail
    -0.07
    突然
    -0.07
    _MAIL
    -0.06
     �
    -0.06
     banging
    -0.06
     titten
    -0.06
    POSITIVE LOGITS
     Corpus
    0.08
     corpus
    0.08
    _corpus
    0.07
     appraisal
    0.07
    RC
    0.07
     phy
    0.07
     mrb
    0.07
    woocommerce
    0.06
    pus
    0.06
    bib
    0.06
    Act Density 0.003%

    No Known Activations