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

    Neuronpedia

    INDEX
    Explanations

    neut

    np_max-act · gemini-2.0-flash

    The neuron chiefly detects mentions of the white‐blood‐cell subtype “neutrophils.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    átky
    -0.07
     الح
    -0.07
     долж
    -0.07
     houses
    -0.07
     Arc
    -0.07
    _funcs
    -0.07
     сфері
    -0.07
    bagai
    -0.07
    ombie
    -0.07
     increment
    -0.06
    POSITIVE LOGITS
     neut
    0.11
    _EMIT
    0.08
    ut
    0.07
    et
    0.07
    UT
    0.07
    ุท
    0.07
     neutron
    0.07
     textured
    0.07
     "_"
    0.07
     aft
    0.06
    Act Density 0.003%

    No Known Activations