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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    This neuron detects numeric literal tokens (especially floating‐point numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    sv
    -0.07
    Blockly
    -0.07
    .Decimal
    -0.06
     acomp
    -0.06
     smokers
    -0.06
     市
    -0.06
    [level
    -0.06
    gtest
    -0.06
     teachers
    -0.06
     mentors
    -0.06
    POSITIVE LOGITS
     كس
    0.06
    _PRIVATE
    0.06
     حسين
    0.06
     заболевания
    0.06
     bitte
    0.06
    '}),↵
    0.06
     української
    0.06
    -fields
    0.05
     کاهش
    0.05
     ऐस
    0.05
    Act Density 0.074%

    No Known Activations