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

    Neuronpedia

    INDEX
    Explanations

    ular

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on technical or domain‐specific multi-syllabic terms (e.g. specialized scientific, medical, or proper-name jargon).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ูก
    -0.07
    	step
    -0.07
    Hour
    -0.06
    舉
    -0.06
     lần
    -0.06
    XC
    -0.06
    )set
    -0.06
     пут
    -0.06
    tuk
    -0.06
    priv
    -0.06
    POSITIVE LOGITS
     yönet
    0.06
    nému
    0.06
     Latvia
    0.06
    дел
    0.06
     zku
    0.06
     Rodrigo
    0.06
    abant
    0.06
     arrogance
    0.06
     Wander
    0.06
    .RES
    0.06
    Act Density 0.287%

    No Known Activations