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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     أث
    -0.08
     ổn
    -0.07
     invasion
    -0.07
     south
    -0.07
     Years
    -0.07
    φό
    -0.06
    south
    -0.06
     sling
    -0.06
     SESSION
    -0.06
     mortality
    -0.06
    POSITIVE LOGITS
    .AutoScaleMode
    0.06
    …I
    0.06
    _COMPLEX
    0.06
     ауд
    0.06
    Conditional
    0.06
    +#
    0.06
     EntityState
    0.05
    リカ
    0.05
     في
    0.05
    ierarchy
    0.05
    Act Density 0.002%

    No Known Activations