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
    .Workflow
    -0.08
    abilidades
    -0.08
    摩
    -0.08
    attributes
    -0.07
     muff
    -0.07
     merece
    -0.07
     صف
    -0.07
     ಸಂಪ
    -0.07
    anyo
    -0.07
     מעט
    -0.07
    POSITIVE LOGITS
    _cash
    0.08
     liés
    0.08
    ダー
    0.08
    주시
    0.08
     Presented
    0.08
     hum
    0.07
     провести
    0.07
    ว่าจะ
    0.07
     financiers
    0.07
     koron
    0.07
    Act Density 0.017%

    No Known Activations