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

    Neuronpedia

    INDEX
    Explanations

    key

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric literals (integer or decimal values) in the schema definitions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Д
    -0.07
     nullptr
    -0.06
    }))
    -0.06
     نقشه
    -0.06
    ูร
    -0.06
     트
    -0.06
    울
    -0.06
    Exposed
    -0.06
     noen
    -0.06
    browse
    -0.06
    POSITIVE LOGITS
    콜걸
    0.07
    λη
    0.06
    crease
    0.06
     probable
    0.06
    probante
    0.06
    ляє
    0.06
    YSIS
    0.06
     immensely
    0.06
    (bounds
    0.06
    .devices
    0.06
    Act Density 0.005%

    No Known Activations