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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _stride
    -0.07
    perse
    -0.06
    يو
    -0.06
    _categorical
    -0.06
     �
    -0.06
     �
    -0.06
    Kill
    -0.06
    _if
    -0.06
     Enables
    -0.06
    Israeli
    -0.06
    POSITIVE LOGITS
     compassionate
    0.07
    .object
    0.07
    ICS
    0.07
    ::↵
    0.06
    >();↵↵
    0.06
     >↵
    0.06
    .List
    0.06
    :S
    0.06
     panties
    0.06
    academic
    0.06
    Act Density 0.000%

    No Known Activations