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

    Neuronpedia

    INDEX
    Explanations

    Categories and areas of interest

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the root “colleg” (as in collegiate/intercollegiate contexts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    nam
    -0.07
     z
    -0.07
     civilization
    -0.07
     xv
    -0.06
    ool
    -0.06
     contaminated
    -0.06
     select
    -0.06
    select
    -0.06
     encouragement
    -0.06
    -db
    -0.06
    POSITIVE LOGITS
     auc
    0.08
     irr
    0.07
    _LR
    0.06
     borderBottom
    0.06
    -fat
    0.06
    ativa
    0.06
     Uncategorized
    0.06
     hâl
    0.06
     Александр
    0.06
     reluct
    0.06
    Act Density 0.321%

    No Known Activations