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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    The neuron fires on technical/programming jargon—words like “argument,” “template,” “execution,” and similar code-oriented terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Toolbar
    -0.06
    -0.06
    Port
    -0.06
    GPU
    -0.06
     looks
    -0.06
     hug
    -0.06
    표
    -0.06
    /repository
    -0.06
     que
    -0.06
    [y
    -0.06
    POSITIVE LOGITS
     dele
    0.07
     Fehler
    0.06
     Battles
    0.06
    寫
    0.06
    _sections
    0.06
    _Event
    0.06
     떨어
    0.06
    ienie
    0.06
     clich
    0.06
     LIN
    0.06
    Act Density 0.899%

    No Known Activations