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

    Neuronpedia

    INDEX
    Explanations

    Medical/Technical issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Safe
    -0.58
     risk
    -0.52
     warning
    -0.51
    Safe
    -0.51
     protection
    -0.49
     dangerous
    -0.48
     safety
    -0.48
     warn
    -0.46
     danger
    -0.46
    afety
    -0.45
    POSITIVE LOGITS
    WithIOException
    0.84
     informée
    0.83
     Reſ
    0.82
     Anſ
    0.80
     kasarigan
    0.79
     Theſe
    0.79
     themſelves
    0.78
     $_"
    0.78
    NameInMap
    0.77
     Jefus
    0.77
    Act Density 0.015%

    No Known Activations