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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Setter
    -0.07
    股东
    -0.06
    that
    -0.06
     uncover
    -0.06
    .cast
    -0.06
     حم
    -0.06
     DESC
    -0.06
    issor
    -0.06
    941
    -0.06
    Jer
    -0.06
    POSITIVE LOGITS
    $query
    0.07
     depressive
    0.07
     tease
    0.07
    _message
    0.07
     Prim
    0.06
    Temperature
    0.06
    氏
    0.06
    (completion
    0.06
    आर
    0.06
    Cargo
    0.06
    Act Density 0.021%

    No Known Activations