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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric literal tokens, especially decimal (floating-point) numbers in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    starting
    -0.06
     agencies
    -0.06
    랙
    -0.06
     wurden
    -0.06
     Mods
    -0.06
     Essentials
    -0.06
    Ctl
    -0.06
    avadoc
    -0.06
    port
    -0.06
    uffs
    -0.06
    POSITIVE LOGITS
     بالم
    0.07
     opendir
    0.07
     تقد
    0.06
     предпри
    0.06
     önünde
    0.06
     자연
    0.06
    보다
    0.06
    _STAGE
    0.06
    怎么
    0.06
     زیادی
    0.06
    Act Density 0.393%

    No Known Activations