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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash

    This neuron detects complex chemical compound names or identifiers (e.g. multi-part IUPAC-style names with numbers, brackets, and hyphens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ******↵↵
    -0.07
     homeland
    -0.07
    最佳
    -0.07
     Jahres
    -0.06
     got
    -0.06
    visions
    -0.06
    南省
    -0.06
    生产
    -0.06
    區
    -0.06
    大量
    -0.06
    POSITIVE LOGITS
    ��
    0.07
    '.$
    0.06
     Sabb
    0.06
    =p
    0.06
    .att
    0.06
     scrolling
    0.06
    _ARGS
    0.06
     undermin
    0.06
     Entre
    0.06
     artic
    0.06
    Act Density 0.070%

    No Known Activations