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

    Neuronpedia

    INDEX
    Explanations

    read more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    National
    -0.07
    RoleId
    -0.06
    prefix
    -0.06
    ‌هایی
    -0.06
    Av
    -0.06
    Any
    -0.06
    ForEach
    -0.06
     Waste
    -0.06
    _positive
    -0.06
    _COUNTER
    -0.06
    POSITIVE LOGITS
     선
    0.07
    <<<<
    0.07
    488
    0.06
     없이
    0.06
     TW
    0.06
     міг
    0.06
     aos
    0.06
    (土
    0.06
     })();↵
    0.06
    _stub
    0.06
    Act Density 0.037%

    No Known Activations