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

    Neuronpedia

    INDEX
    Explanations

    Referring to figures

    np_max-act · gemini-2.0-flash

    The neuron flags occurrences of patent‐style figure call‐outs (e.g. “FIG.” and its associated punctuation).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    technical terms related to inventions and mechanical devices.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Born
    -0.07
    edy
    -0.07
    Monday
    -0.07
    RELEASE
    -0.06
    \Catalog
    -0.06
    onitor
    -0.06
     creature
    -0.06
     ley
    -0.06
    avad
    -0.06
    stretch
    -0.06
    POSITIVE LOGITS
    时候
    0.07
    ;',
    0.07
     Ruth
    0.06
    ByExample
    0.06
    IFIER
    0.06
    ;'↵
    0.06
     buddies
    0.06
    +'&
    0.06
     후
    0.06
     trò
    0.06
    Act Density 0.002%

    No Known Activations