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

    Neuronpedia

    INDEX
    Explanations

    counteracting

    np_max-act · gemini-2.0-flash

    The neuron fires on verbs (like “disarm,” “neutralize,” “deactivate,” “disable”) that describe rendering a dangerous device (e.g. a bomb) safe.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    째
    -0.07
    -normal
    -0.06
     Offering
    -0.06
    izziness
    -0.06
     khởi
    -0.06
     sucht
    -0.06
    change
    -0.06
    암
    -0.06
    产
    -0.06
    دث
    -0.06
    POSITIVE LOGITS
     Jen
    0.07
     immobil
    0.07
     valuation
    0.06
    (ff
    0.06
     kh
    0.06
    .toJson
    0.06
    bases
    0.06
     것입니다
    0.06
     význam
    0.06
     QDom
    0.06
    Act Density 0.012%

    No Known Activations