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 occurrences of generic type parameters and single-letter type or parameter identifiers in code (e.g. T, A, S, U in type declarations and function parameter lists).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     سوم
    -0.07
    :"",
    -0.06
     عب
    -0.06
    ologie
    -0.06
    cdf
    -0.06
    <select
    -0.06
    .scss
    -0.06
     fotbal
    -0.06
    _PARAM
    -0.06
    :pointer
    -0.06
    POSITIVE LOGITS
    ।↵
    0.07
     stopped
    0.07
     ήταν
    0.07
    /">
    0.07
     attached
    0.07
     vibrant
    0.07
     handwritten
    0.07
     simply
    0.06
    џџ
    0.06
    /I
    0.06
    Act Density 0.025%

    No Known Activations