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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash

    This neuron specializes in detecting numeric literals (especially floating-point constants) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .option
    -0.07
    TU
    -0.07
     Psychology
    -0.07
    pesan
    -0.06
    ोव
    -0.06
    _memory
    -0.06
    	angle
    -0.06
    альные
    -0.06
     piles
    -0.06
    Mem
    -0.06
    POSITIVE LOGITS
    Slot
    0.06
    救
    0.06
    —at
    0.06
     ToolStrip
    0.06
     好
    0.06
     행
    0.06
     Champ
    0.06
    .pages
    0.06
    .Produ
    0.06
     الجم
    0.05
    Act Density 0.002%

    No Known Activations