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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash

    This neuron detects the special control tokens (e.g. the `<|…|>` markers like `<|end_header_id|>`) used to delimit or annotate parts of the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     strained
    -0.07
     Bradford
    -0.07
     italian
    -0.06
    errmsg
    -0.06
     кле
    -0.06
     dum
    -0.06
    bread
    -0.06
     HW
    -0.06
    AREST
    -0.06
     effet
    -0.06
    POSITIVE LOGITS
    ности
    0.06
    ivr
    0.06
    場合は
    0.06
    Alignment
    0.06
     انجمن
    0.06
     floatValue
    0.06
     SetProperty
    0.06
    .about
    0.06
     rámci
    0.06
     Leading
    0.06
    Act Density 0.044%

    No Known Activations