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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Anyway
    -0.07
     CI
    -0.06
     TY
    -0.06
    (feature
    -0.06
    ，只
    -0.06
    names
    -0.06
    $:
    -0.06
    és
    -0.06
    )this
    -0.06
    XXXXXXXX
    -0.06
    POSITIVE LOGITS
     профес
    0.07
    .XtraGrid
    0.07
    .writeObject
    0.07
    .`
    0.07
     گردد
    0.07
     skys
    0.06
     Webseite
    0.06
     рух
    0.06
    ительной
    0.06
     आख
    0.06
    Act Density 0.138%

    No Known Activations