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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -agent
    -0.08
    �
    -0.07
     cient
    -0.07
    стоя
    -0.06
    /h
    -0.06
    ratio
    -0.06
    thr
    -0.06
     임
    -0.06
     seeming
    -0.06
    ặ
    -0.06
    POSITIVE LOGITS
     Doğu
    0.07
    -redux
    0.06
    $start
    0.06
     println
    0.06
     Juli
    0.06
    MaxY
    0.06
     Schneider
    0.06
    ledon
    0.06
    RegExp
    0.06
     CZ
    0.06
    Act Density 0.096%

    No Known Activations