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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron activates on territorial place names used in aristocratic titles (e.g. estate, region, or constituency names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     nanoparticles
    -0.07
    ам
    -0.07
     protagonists
    -0.07
     />,↵
    -0.07
    щини
    -0.07
    Wilson
    -0.06
     Lotto
    -0.06
    ..↵↵↵↵
    -0.06
     knack
    -0.06
    زة
    -0.06
    POSITIVE LOGITS
     confirming
    0.07
    (adapter
    0.06
    シア
    0.06
    uty
    0.06
    QUENCY
    0.06
     niż
    0.06
     inset
    0.06
     modeled
    0.06
     acquiring
    0.06
     vas
    0.06
    Act Density 0.005%

    No Known Activations