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

    Neuronpedia

    INDEX
    Explanations

    alpha

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    azers
    -0.07
    Keyboard
    -0.07
    Spider
    -0.07
     ice
    -0.06
    cek
    -0.06
    apa
    -0.06
    estival
    -0.06
     Sheridan
    -0.06
     mirrors
    -0.06
    asionally
    -0.06
    POSITIVE LOGITS
     proceed
    0.07
    änder
    0.07
     Calcium
    0.06
     craftsmanship
    0.06
    _SERVICE
    0.06
    "><?=$
    0.06
     производства
    0.06
     حج
    0.06
    \<
    0.06
     Çağ
    0.06
    Act Density 0.004%

    No Known Activations