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

    Neuronpedia

    INDEX
    Explanations

    progress

    np_max-act · gemini-2.0-flash

    The neuron fires on language describing qualification or requirement criteria—phrases about meeting, satisfying, or applying specific conditions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     packed
    -0.07
    ynam
    -0.06
    ğitim
    -0.06
    Pokud
    -0.06
     подраз
    -0.06
    ительность
    -0.06
    ,cljs
    -0.06
     geri
    -0.06
     convex
    -0.06
    gow
    -0.06
    POSITIVE LOGITS
    Buttons
    0.07
    getSource
    0.07
    ости
    0.06
     xmin
    0.06
    quired
    0.06
    laş
    0.06
    _self
    0.06
    .StatusCode
    0.06
    losure
    0.06
    ll
    0.06
    Act Density 0.032%

    No Known Activations