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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intimidated
    -0.07
    еної
    -0.07
     Psychiat
    -0.06
     stick
    -0.06
     banana
    -0.06
     extracted
    -0.06
    筆
    -0.06
     Valid
    -0.06
    Publish
    -0.06
     citrus
    -0.06
    POSITIVE LOGITS
    .KeyCode
    0.06
    /portfolio
    0.06
    _Options
    0.06
     وق
    0.06
    ]</
    0.06
     motive
    0.06
     quota
    0.06
     Unter
    0.06
     executive
    0.06
     marry
    0.06
    Act Density 0.064%

    No Known Activations