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

    Neuronpedia

    INDEX
    Explanations

    aml

    np_max-act · gemini-2.0-flash

    The neuron is firing on tokens that name or denote OCaml/Coq source-code elements (e.g. “ocaml,” “.ml,” “coq,” language-specific module or command names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    QUE
    -0.07
     QRect
    -0.07
    ิภาพ
    -0.07
    itele
    -0.07
    icer
    -0.07
     Bean
    -0.07
     stead
    -0.06
    SAMPLE
    -0.06
    LayoutPanel
    -0.06
    ¨¨
    -0.06
    POSITIVE LOGITS
    manuel
    0.06
    toMatch
    0.06
    (il
    0.06
     prosecute
    0.06
     얼마
    0.06
    :f
    0.06
     insane
    0.06
    :=
    0.06
     expérience
    0.06
    ():
    0.06
    Act Density 0.005%

    No Known Activations