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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash

    This neuron responds to two-word phrasal-verb constructions with a motion verb followed by “out” (e.g. “break out,” “pull out,” “haul out,” “whip out”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    くれる
    -0.07
     Zoo
    -0.07
    .cap
    -0.07
    -ca
    -0.07
    .protocol
    -0.07
     مدیریت
    -0.07
    ousy
    -0.07
    (scores
    -0.07
    .plot
    -0.06
    -Nov
    -0.06
    POSITIVE LOGITS
     setUser
    0.07
    Ini
    0.07
    оры
    0.06
    ")]
    0.06
    outfile
    0.06
    metric
    0.06
    /sample
    0.06
    dad
    0.06
    _cre
    0.06
    laştır
    0.06
    Act Density 0.011%

    No Known Activations