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

    Neuronpedia

    INDEX
    Explanations

    summing

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens (especially decimal or floating-point values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     inadvertently
    -0.06
    fade
    -0.06
    ่อง
    -0.06
     zaměst
    -0.06
    这个
    -0.06
     Ten
    -0.06
    egal
    -0.06
    .shell
    -0.06
     حرف
    -0.06
    ीवन
    -0.06
    POSITIVE LOGITS
    (tok
    0.07
    ('_',
    0.06
     →
    0.06
    (rc
    0.06
     лік
    0.06
    ."↵↵↵↵
    0.06
    ("#{
    0.06
    λι
    0.06
     BigNumber
    0.06
    -plus
    0.06
    Act Density 0.017%

    No Known Activations