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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    This neuron fires on vector‐array positions where at least one coordinate is exactly zero (i.e. detects indices of points with any zero component).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     SVM
    -0.07
     blk
    -0.06
     fingerprint
    -0.06
     metrů
    -0.06
    OMBRE
    -0.06
    Deaths
    -0.06
     кількості
    -0.06
    ์
    -0.06
    elp
    -0.06
     Mutation
    -0.06
    POSITIVE LOGITS
    .thread
    0.06
    .tie
    0.06
    submitButton
    0.06
    _LSB
    0.06
     Npgsql
    0.06
     Thời
    0.06
     wrongful
    0.06
    dens
    0.06
    \Php
    0.06
    _ds
    0.06
    Act Density 0.006%

    No Known Activations