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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on vague “filler” tokens (like “etc,” “more,” “lots,” “rest,” ellipses, etc.) that signal omitted or generic continuation rather than substantive content.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    eos
    -0.08
    aram
    -0.07
    vert
    -0.07
    처
    -0.07
     Ad
    -0.07
    을
    -0.06
     McGregor
    -0.06
    )t
    -0.06
    ired
    -0.06
    ึกษ
    -0.06
    POSITIVE LOGITS
     diminish
    0.06
     inventions
    0.06
    くらい
    0.06
    760
    0.06
    ophone
    0.06
    Src
    0.06
     clarity
    0.06
     OU
    0.06
    391
    0.06
     prospect
    0.06
    Act Density 0.017%

    No Known Activations