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

    Neuronpedia

    INDEX
    Explanations

    Code styling: Borders

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals—particularly decimal (floating-point) values in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _hook
    -0.07
    negative
    -0.07
     女
    -0.06
    Presentation
    -0.06
     Tue
    -0.06
    Forward
    -0.06
     excelente
    -0.06
     barrel
    -0.06
    итив
    -0.06
    shield
    -0.06
    POSITIVE LOGITS
     öğret
    0.06
     CentOS
    0.06
    にして
    0.06
    <iostream
    0.06
     élect
    0.06
    ogram
    0.06
     imkân
    0.06
    いう
    0.06
    (chat
    0.06
    として
    0.06
    Act Density 0.002%

    No Known Activations