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

    Neuronpedia

    INDEX
    Explanations

    Code/configuration files

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens—especially decimal numbers—identifying floating‐point values in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     عالی
    -0.07
     pathname
    -0.07
    де
    -0.07
     dull
    -0.07
    察
    -0.06
     환산
    -0.06
    analyze
    -0.06
     Sentry
    -0.06
     lock
    -0.06
     Killing
    -0.06
    POSITIVE LOGITS
    开始
    0.06
     fakt
    0.06
     tarihli
    0.06
     irritating
    0.06
    implement
    0.06
    createCommand
    0.06
     aktu
    0.06
    .parseColor
    0.06
     Télé
    0.06
    yh
    0.05
    Act Density 0.048%

    No Known Activations