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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numerical measurement tokens (especially decimal or floating‐point values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    %",↵
    -0.06
    ,set
    -0.06
     jej
    -0.06
    %"
    -0.06
    Ds
    -0.06
     は
    -0.06
    Modules
    -0.06
    ingt
    -0.06
    argon
    -0.06
     Ne
    -0.06
    POSITIVE LOGITS
    dbContext
    0.07
    900
    0.07
    ул
    0.06
     getPrice
    0.06
     شناخته
    0.06
    \OptionsResolver
    0.06
     belonged
    0.06
    \Client
    0.06
     див
    0.06
    _ACT
    0.06
    Act Density 0.052%

    No Known Activations