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

    Neuronpedia

    INDEX
    Explanations

    app

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .height
    -0.07
    Persistence
    -0.07
    óc
    -0.07
    α
    -0.07
     aggregate
    -0.07
    ?:
    -0.07
    .arg
    -0.06
    force
    -0.06
     Hemp
    -0.06
     rak
    -0.06
    POSITIVE LOGITS
     вы
    0.07
    udson
    0.07
     Ч
    0.06
    _EXTENDED
    0.06
    tparam
    0.06
     protective
    0.06
    _Osc
    0.06
     Contrib
    0.06
     поход
    0.06
    픈
    0.06
    Act Density 0.013%

    No Known Activations