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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron responds to CSS framework grid class names (e.g. the “col-*-*” Bootstrap column tokens) indicating layout columns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     не
    -0.06
    ีช
    -0.06
    إنجليزية
    -0.06
    bm
    -0.06
    Ik
    -0.06
    wu
    -0.06
    cks
    -0.06
     कह
    -0.06
    _wc
    -0.06
    bottom
    -0.06
    POSITIVE LOGITS
    @Repository
    0.07
    .Child
    0.06
     matures
    0.06
     Marriage
    0.06
    liğine
    0.06
     gql
    0.06
    络
    0.06
     expl
    0.06
     grant
    0.06
    йте
    0.06
    Act Density 0.065%

    No Known Activations