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

    Neuronpedia

    INDEX
    Explanations

    convolution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ngOnDestroy
    -0.07
     ActiveRecord
    -0.06
    инку
    -0.06
    uppet
    -0.06
     Hate
    -0.06
     Hairst
    -0.06
     XL
    -0.06
    .forName
    -0.06
    ظة
    -0.06
    .handlers
    -0.06
    POSITIVE LOGITS
     adverse
    0.07
    colon
    0.06
     aquatic
    0.06
    815
    0.06
    inclusive
    0.06
     buds
    0.06
     circumstance
    0.06
     SI
    0.06
    asar
    0.06
     tudo
    0.06
    Act Density 0.008%

    No Known Activations