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

    Neuronpedia

    INDEX
    Explanations

    us

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ста
    -0.06
     SY
    -0.06
     Whe
    -0.05
    İSİ
    -0.05
     Blockchain
    -0.05
     способ
    -0.05
     можно
    -0.05
    auen
    -0.05
    "],["
    -0.05
    -po
    -0.05
    POSITIVE LOGITS
     burger
    0.07
    agra
    0.07
    UiThread
    0.07
    d
    0.06
    ื้
    0.06
    �
    0.06
     dh
    0.06
     vỏ
    0.06
    _d
    0.06
     مس
    0.06
    Act Density 0.000%

    No Known Activations