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

    Neuronpedia

    INDEX
    Explanations

    el

    np_max-act · gemini-2.0-flash

    This neuron fires on specialized technical terms—especially subwords of laboratory methods, chemicals, materials, and related jargon.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     NT
    -0.07
    高等
    -0.06
     Frankie
    -0.06
    аг
    -0.06
    /to
    -0.06
     तम
    -0.06
    _ALIAS
    -0.06
    Leave
    -0.06
    ump
    -0.06
     destinations
    -0.06
    POSITIVE LOGITS
    าหาร
    0.07
    ามารถ
    0.07
    ляет
    0.07
    posing
    0.07
     بزرگ
    0.06
     ApplicationUser
    0.06
    lu
    0.06
     طبي
    0.06
    warz
    0.06
     useRouter
    0.06
    Act Density 0.080%

    No Known Activations