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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on decimal‐point–containing numeric tokens (floating-point literals) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    transform
    -0.06
     VPN
    -0.06
     механи
    -0.06
     hierarchy
    -0.06
    .range
    -0.06
    WER
    -0.06
    Ò
    -0.06
     transform
    -0.06
    .RunWith
    -0.06
    AI
    -0.06
    POSITIVE LOGITS
    liğin
    0.07
    ').'
    0.06
    lacağı
    0.06
     nelle
    0.06
     localtime
    0.06
     staple
    0.06
    InnerText
    0.06
     बद
    0.06
     taxis
    0.06
    cmpeq
    0.06
    Act Density 0.040%

    No Known Activations