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

    Neuronpedia

    INDEX
    Explanations

    How's it going?

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .tr
    -0.08
     Pres
    -0.08
    \web
    -0.07
    (upload
    -0.07
    _unc
    -0.07
     stripping
    -0.07
    草莓
    -0.07
    铱
    -0.07
     EventArgs
    -0.07
    .But
    -0.07
    POSITIVE LOGITS
     движ
    0.07
     participação
    0.07
     DAMAGES
    0.07
     fallback
    0.07
     =================================================
    0.06
     mange
    0.06
     skewed
    0.06
    ogene
    0.06
    klass
    0.06
     Interrupt
    0.06
    Act Density 0.028%

    No Known Activations