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

    Neuronpedia

    INDEX
    Explanations

    prefixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ApplicationException
    -0.07
     Media
    -0.07
    .FloatField
    -0.06
    INCLUDE
    -0.06
     Belgium
    -0.06
     Expression
    -0.06
     uncertainties
    -0.06
    yl
    -0.06
     DL
    -0.06
    schemas
    -0.06
    POSITIVE LOGITS
     distracting
    0.06
    deck
    0.06
     sque
    0.06
     disemb
    0.06
     push
    0.06
    _ph
    0.06
     hebben
    0.06
    SR
    0.05
     Tops
    0.05
     spl
    0.05
    Act Density 0.008%

    No Known Activations