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

    Neuronpedia

    INDEX
    Explanations

    stories about people

    np_max-act · gemini-2.0-flash

    The neuron fires on personal proper names and biographical identifiers (e.g. individual names, titles, and age markers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    урс
    -0.07
    idae
    -0.06
    AJOR
    -0.06
    效果
    -0.06
    xl
    -0.06
    _rd
    -0.06
    draft
    -0.06
     Diff
    -0.06
     thổ
    -0.06
    	KEY
    -0.06
    POSITIVE LOGITS
     jean
    0.06
     gehen
    0.06
    ै↵
    0.06
    РН
    0.06
     World
    0.06
     persec
    0.06
     代
    0.06
     THAN
    0.06
    (...)↵
    0.06
     interpreter
    0.06
    Act Density 0.051%

    No Known Activations