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

    Neuronpedia

    INDEX
    Explanations

    sciences

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on names of academic disciplines or subject‐area titles.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    vens
    -0.07
    (gen
    -0.06
    }\\
    -0.06
     Dust
    -0.06
     Camp
    -0.06
     sailors
    -0.06
    .matmul
    -0.06
     ellipt
    -0.06
     ["
    -0.06
    Svg
    -0.06
    POSITIVE LOGITS
     sciences
    0.11
     Arts
    0.11
     arts
    0.11
     Sciences
    0.08
     senses
    0.07
     contrary
    0.07
     Humanities
    0.07
    Actions
    0.07
     Highlands
    0.07
     SCI
    0.07
    Act Density 0.019%

    No Known Activations