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

    Neuronpedia

    INDEX
    Explanations

    defects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    חיל
    -0.07
    ysi
    -0.07
    节目
    -0.06
    ULE
    -0.06
    PERTIES
    -0.06
     çevir
    -0.06
    ici
    -0.06
     physic
    -0.06
    환
    -0.06
     инвести
    -0.06
    POSITIVE LOGITS
    论述
    0.08
    �
    0.07
     acclaim
    0.07
    美妆
    0.07
     Islanders
    0.07
    앎
    0.07
    惚
    0.07
    堐
    0.07
     Gaming
    0.07
     đất
    0.07
    Act Density 0.026%

    No Known Activations