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

    Neuronpedia

    INDEX
    Explanations

    severity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     irradi
    -0.07
    (p
    -0.07
     vezes
    -0.07
    FDA
    -0.07
    881
    -0.07
    會
    -0.06
     cuerpo
    -0.06
    (c
    -0.06
    ,True
    -0.06
    Š
    -0.06
    POSITIVE LOGITS
     severity
    0.35
     Severity
    0.25
    severity
    0.17
    Severity
    0.16
    verity
    0.12
     seriousness
    0.07
     Soap
    0.07
     advent
    0.07
    центра
    0.07
    erge
    0.06
    Act Density 0.002%

    No Known Activations