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

    Neuronpedia

    INDEX
    Explanations

    say ",cv"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mediate
    -0.08
    _validation
    -0.08
    -button
    -0.07
     liver
    -0.07
    (filename
    -0.07
    _int
    -0.07
     nominate
    -0.07
    (boolean
    -0.07
    _files
    -0.07
    -ver
    -0.06
    POSITIVE LOGITS
    ام
    0.07
     qued
    0.06
     الرسمي
    0.06
     aerospace
    0.06
     fleeting
    0.06
     incid
    0.05
     muže
    0.05
     twee
    0.05
    *****↵↵
    0.05
    .Entities
    0.05
    Act Density 0.010%

    No Known Activations