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

    Neuronpedia

    INDEX
    Explanations

    sigma

    np_max-act · gemini-2.0-flash

    The neuron fires on LaTeX‐style mathematical notation, especially Greek letter symbols (e.g. γ, Γ, σ) and related formula tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Moreno
    -0.07
     Batter
    -0.07
    oke
    -0.07
    _multip
    -0.07
     زر
    -0.07
     vids
    -0.07
     padx
    -0.06
     Translator
    -0.06
    атар
    -0.06
     BK
    -0.06
    POSITIVE LOGITS
    Democratic
    0.06
    criminal
    0.06
    (([
    0.06
    附近
    0.06
    OMATIC
    0.06
    tesy
    0.06
    ايت
    0.06
     Authors
    0.06
     ;↵
    0.06
     内
    0.06
    Act Density 0.001%

    No Known Activations