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

    Neuronpedia

    INDEX
    Explanations

    Errors, corrections, disagreements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .substr
    -0.08
    _fatal
    -0.07
    очно
    -0.07
     tag
    -0.07
    \Log
    -0.07
    bomb
    -0.06
     огра
    -0.06
    AMP
    -0.06
    .scalar
    -0.06
     cortisol
    -0.06
    POSITIVE LOGITS
     Pussy
    0.07
    lub
    0.06
    application
    0.06
     Saint
    0.06
     Junk
    0.06
     continent
    0.06
    หาย
    0.06
     CLR
    0.06
    ινή
    0.06
    MethodInfo
    0.06
    Act Density 0.021%

    No Known Activations