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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash

    commands and functions related to programming languages, particularly those based on lambda calculus.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects LaTeX command names (the control‐word strings following a backslash).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    cích
    -0.07
    getColor
    -0.07
    なお
    -0.07
    �
    -0.06
    、三
    -0.06
     брат
    -0.06
    Sound
    -0.06
    .Utils
    -0.06
     Casa
    -0.06
     unters
    -0.06
    POSITIVE LOGITS
    ;}
    0.06
     мож
    0.06
    ㅠㅠ
    0.06
    (artist
    0.06
    +↵
    0.06
     bö
    0.06
     この
    0.06
    ??
    0.06
     INF
    0.06
    efully
    0.06
    Act Density 0.041%

    No Known Activations