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

    Neuronpedia

    INDEX
    Explanations

    politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -facing
    -0.07
    -confirm
    -0.07
    descending
    -0.07
     лаборатор
    -0.07
     coefficient
    -0.07
     моч
    -0.06
     فول
    -0.06
    с
    -0.06
    -effective
    -0.06
    FD
    -0.06
    POSITIVE LOGITS
    lbs
    0.07
     antib
    0.06
     dif
    0.06
     Rangers
    0.06
     BIT
    0.06
    alach
    0.06
     BALL
    0.06
    urry
    0.06
     quello
    0.06
    ทะ
    0.05
    Act Density 0.145%

    No Known Activations