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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the programming‐related identifier “Range,” marking references to a code object or class named Range.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ITED
    -0.07
    uates
    -0.06
     Retirement
    -0.06
    (sigma
    -0.06
     ﾍ
    -0.06
    +"]
    -0.06
    írk
    -0.06
    tabpanel
    -0.06
    ees
    -0.06
    #↵
    -0.06
    POSITIVE LOGITS
    اوند
    0.07
     puta
    0.07
    ुत
    0.07
     jeunes
    0.07
     obrig
    0.07
     sparkle
    0.06
    ellido
    0.06
    .setStyle
    0.06
     sitios
    0.06
    úde
    0.06
    Act Density 0.010%

    No Known Activations