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

    Neuronpedia

    INDEX
    Explanations

    genetics and mutations

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on numeric tokens—especially floating-point and percentage values—i.e. it detects decimal or statistical number expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    /Private
    -0.07
    atters
    -0.07
    aturdays
    -0.07
    JECTED
    -0.07
     IH
    -0.07
    .Mutable
    -0.07
    abetic
    -0.07
    enco
    -0.07
    oret
    -0.07
    レット
    -0.07
    POSITIVE LOGITS
     technolog
    0.06
    ══
    0.06
    *s
    0.06
    _KeyPress
    0.06
    "%
    0.06
     tidak
    0.05
    (mysql
    0.05
     (![
    0.05
    elage
    0.05
     ขาย
    0.05
    Act Density 0.100%

    No Known Activations