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

    Neuronpedia

    INDEX
    Explanations

    code/garbled text

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on numeric values—especially decimal numbers—within tabular or data‐lookup sections.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .interpolate
    -0.07
    aka
    -0.06
     До
    -0.06
     //////
    -0.06
    Hugh
    -0.06
    <>
    -0.06
    ไฟ
    -0.06
    _owner
    -0.06
     ≤
    -0.06
     looks
    -0.06
    POSITIVE LOGITS
    Ticker
    0.06
     Phillies
    0.06
    _Reset
    0.06
     selectable
    0.06
     MOTOR
    0.06
     semantic
    0.06
     Taiwanese
    0.06
     previous
    0.06
    (';
    0.05
    �
    0.05
    Act Density 0.030%

    No Known Activations