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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Heads
    -0.07
    말
    -0.07
    ゃ
    -0.06
    appearance
    -0.06
    blems
    -0.06
    Ze
    -0.06
    Estimated
    -0.06
    ضاء
    -0.06
     anchored
    -0.06
     Uran
    -0.06
    POSITIVE LOGITS
     xr
    0.07
    154
    0.06
    enburg
    0.06
     "+
    0.06
    utenberg
    0.06
     vx
    0.06
    일본
    0.06
    164
    0.06
    <dd
    0.06
    Symfony
    0.06
    Act Density 0.030%

    No Known Activations