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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    พวก
    -0.06
    interopRequire
    -0.06
    (with
    -0.06
     بیشتر
    -0.06
    NEXT
    -0.06
    陆
    -0.06
    pieces
    -0.06
    players
    -0.06
     DAG
    -0.06
    混合
    -0.06
    POSITIVE LOGITS
    _EM
    0.07
     Class
    0.06
     undermining
    0.06
    .cf
    0.06
    -options
    0.06
     arası
    0.06
    ensem
    0.06
     Approximately
    0.06
     Environment
    0.06
    .pen
    0.06
    Act Density 0.084%

    No Known Activations