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

    Neuronpedia

    INDEX
    Explanations

    trim

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _buckets
    -0.06
    iap
    -0.06
    ytt
    -0.06
    うち
    -0.06
    (cookie
    -0.06
     IEntity
    -0.06
    bullet
    -0.06
     specialties
    -0.06
    _tunnel
    -0.06
    urtle
    -0.06
    POSITIVE LOGITS
     произ
    0.07
    .frequency
    0.06
    }')↵↵
    0.06
    _GPU
    0.06
     Tooth
    0.06
    ись
    0.06
    ulously
    0.06
    ISE
    0.06
    .WEST
    0.06
    .audio
    0.06
    Act Density 0.003%

    No Known Activations