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

    Neuronpedia

    INDEX
    Explanations

    prompt

    np_max-act · gemini-2.0-flash

    The neuron fires on the “prompt:” marker in the header, i.e. the literal token “prompt” (and its trailing colon).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Archie
    -0.07
     Charges
    -0.07
    zim
    -0.07
     обработ
    -0.06
     Effects
    -0.06
    ологія
    -0.06
     contempl
    -0.06
    ots
    -0.06
    福利
    -0.06
    美国
    -0.06
    POSITIVE LOGITS
    opic
    0.07
    _Id
    0.06
    .piece
    0.06
     मह
    0.06
    伴
    0.06
    거
    0.06
     findViewById
    0.06
    184
    0.06
    )->
    0.06
    榜
    0.06
    Act Density 0.007%

    No Known Activations