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

    Neuronpedia

    INDEX
    Explanations

    code loops and conditions

    np_max-act · gemini-2.0-flash

    The neuron activates on floating-point numeric literals in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Heard
    -0.07
    -Ray
    -0.07
    能源
    -0.06
    -tr
    -0.06
    ρή
    -0.06
    zim
    -0.06
     mấy
    -0.06
     što
    -0.06
     malfunction
    -0.06
    _Product
    -0.06
    POSITIVE LOGITS
    .constant
    0.07
     ${↵
    0.07
     descended
    0.06
     antlr
    0.06
     점
    0.06
     ду
    0.06
     soaring
    0.06
     dodge
    0.06
    errorMsg
    0.06
     baktı
    0.06
    Act Density 0.003%

    No Known Activations