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

    Neuronpedia

    INDEX
    Explanations

    warnings and precautions

    np_max-act · gemini-2.0-flash

    The neuron fires on moral-imperative or ethical advice language, especially prohibitions and exhortations (e.g. “always…never steal”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    esiz
    -0.07
     Shapiro
    -0.06
     lĩnh
    -0.06
    cookie
    -0.06
    quality
    -0.06
    iones
    -0.06
    龄
    -0.06
    /sc
    -0.06
     Kou
    -0.06
    STREAM
    -0.06
    POSITIVE LOGITS
     توسعه
    0.07
    CAT
    0.06
    :"",↵
    0.06
     infant
    0.06
     concentrates
    0.06
     dipping
    0.06
     إذا
    0.06
    ượt
    0.06
     Cord
    0.06
    _DDR
    0.06
    Act Density 0.059%

    No Known Activations