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

    Neuronpedia

    INDEX
    Explanations

    ably

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ر
    -0.07
     vigilant
    -0.07
    355
    -0.06
    _ordered
    -0.06
     persistence
    -0.06
    ambiguous
    -0.06
     children
    -0.06
    _argument
    -0.06
     Teen
    -0.06
     lonely
    -0.06
    POSITIVE LOGITS
    시키
    0.07
    \M
    0.06
    icari
    0.06
    >Status
    0.06
     LAS
    0.06
    .GL
    0.06
     проз
    0.06
    Peak
    0.06
     geomet
    0.06
     Blacks
    0.06
    Act Density 0.112%

    No Known Activations