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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اين
    -0.07
    	StringBuffer
    -0.06
    components
    -0.06
    .Geometry
    -0.06
    .write
    -0.06
    .fx
    -0.06
    شت
    -0.06
    .poi
    -0.06
    cing
    -0.06
    .ini
    -0.06
    POSITIVE LOGITS
     semiclass
    0.08
     protect
    0.07
     surgical
    0.06
     Townsend
    0.06
    (send
    0.06
     ^{
    0.06
     nas
    0.06
     лиш
    0.06
     Аб
    0.06
    advisor
    0.06
    Act Density 0.012%

    No Known Activations