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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    including
    -0.06
     positivity
    -0.06
    FI
    -0.06
    |h
    -0.06
     Metro
    -0.06
    rams
    -0.06
     Strand
    -0.06
    警察
    -0.06
     Retail
    -0.06
    =m
    -0.06
    POSITIVE LOGITS
    AUTH
    0.07
    антаж
    0.06
    (passport
    0.06
     enough
    0.06
    ницт
    0.06
     '@
    0.06
     stesso
    0.06
    ‌شود
    0.06
    εύ
    0.06
     hack
    0.06
    Act Density 0.001%

    No Known Activations