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

    Neuronpedia

    INDEX
    Explanations

    deviation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Ch
    -0.07
     role
    -0.07
    ))↵↵↵
    -0.07
    _ACCESS
    -0.06
    ())↵↵↵
    -0.06
    _nome
    -0.06
    欠
    -0.06
    =").
    -0.06
    calc
    -0.06
     {{$
    -0.06
    POSITIVE LOGITS
     deviations
    0.10
    egade
    0.08
     abnormal
    0.08
     errone
    0.07
     deviation
    0.07
    venue
    0.07
     그리
    0.07
     travelling
    0.07
     insulin
    0.07
     teal
    0.07
    Act Density 0.007%

    No Known Activations