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

    Neuronpedia

    INDEX
    Explanations

    rs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pip
    -0.07
    _bh
    -0.07
     curt
    -0.07
     preval
    -0.07
    关注
    -0.07
    eya
    -0.07
    pname
    -0.07
     nær
    -0.07
    精选
    -0.07
     רחב
    -0.07
    POSITIVE LOGITS
    總統
    0.08
     Inter
    0.07
    ismo
    0.07
    OMB
    0.07
    婊
    0.07
    ואי
    0.07
     dialog
    0.06
    izer
    0.06
     Apocalypse
    0.06
     imposition
    0.06
    Act Density 0.000%

    No Known Activations