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

    Neuronpedia

    INDEX
    Explanations

    Taxes and insurance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("../../
    -0.07
    (win
    -0.07
    .est
    -0.07
     زی
    -0.07
    -sensitive
    -0.07
    /host
    -0.06
     کنترل
    -0.06
     separate
    -0.06
     अब
    -0.06
     trava
    -0.06
    POSITIVE LOGITS
    IJ
    0.07
    _FULLSCREEN
    0.07
    attery
    0.06
    爵
    0.06
     Alabama
    0.06
     Cottage
    0.06
     Matters
    0.06
     africa
    0.06
    atan
    0.06
     hookup
    0.06
    Act Density 0.011%

    No Known Activations