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

    Neuronpedia

    INDEX
    Explanations

    directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ocrats
    -0.07
    853
    -0.06
    メージ
    -0.06
    Density
    -0.06
     замов
    -0.06
    вар
    -0.06
    ,title
    -0.06
     resisted
    -0.06
     Helpers
    -0.06
    фі
    -0.06
    POSITIVE LOGITS
    (mean
    0.07
     září
    0.06
    _Label
    0.06
    (l
    0.06
     cameras
    0.06
     btn
    0.06
     sensors
    0.06
    LEN
    0.06
     retina
    0.06
    ern
    0.06
    Act Density 0.014%

    No Known Activations