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

    Neuronpedia

    INDEX
    Explanations

    indefinite articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Handbook
    -0.07
    crate
    -0.07
     handbook
    -0.07
    /ap
    -0.06
     punishing
    -0.06
    .dashboard
    -0.06
    istik
    -0.06
     wget
    -0.06
     control
    -0.06
     cầu
    -0.06
    POSITIVE LOGITS
    */),
    0.06
    '):
    0.06
    [now
    0.06
     />;↵
    0.06
    Reader
    0.06
    _destination
    0.06
     خودش
    0.06
     endereco
    0.06
     갈
    0.06
    provided
    0.06
    Act Density 0.019%

    No Known Activations