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

    Neuronpedia

    INDEX
    Explanations

    academic/historical texts

    np_max-act · gemini-2.0-flash

    The neuron responds to high-level abstract or philosophical keywords (e.g. “importance,” “knowledge,” “concept,” “reason,” “freedom,” “autonomy”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     throwError
    -0.07
    .getService
    -0.07
     exponential
    -0.07
     Sele
    -0.07
     oyuncu
    -0.06
    _RCC
    -0.06
    กำล
    -0.06
    所属
    -0.06
     likeness
    -0.06
     davidjl
    -0.06
    POSITIVE LOGITS
    EX
    0.08
    261
    0.07
     mennes
    0.06
    11
    0.06
    IV
    0.06
    there
    0.06
     Implements
    0.06
     fury
    0.06
    zem
    0.06
    ，只
    0.06
    Act Density 0.081%

    No Known Activations