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

    Neuronpedia

    INDEX
    Explanations

    Narrative passages

    np_max-act · gemini-2.0-flash

    stories involving body confidence and sexual exploration.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The main thing this neuron does is detect narrative-transition cues—words and verbs that signal plot shifts or new events in a story.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     detecting
    -0.06
     PHP
    -0.06
     공
    -0.06
     drinkers
    -0.06
    rav
    -0.06
     Nath
    -0.06
     zi
    -0.06
    (py
    -0.06
     mandates
    -0.06
     tecn
    -0.06
    POSITIVE LOGITS
    ...↵↵
    0.06
    важа
    0.06
    ......↵↵
    0.06
     trest
    0.06
    .titleLabel
    0.06
    _Param
    0.06
    --↵↵
    0.06
     دلار
    0.06
     인기글
    0.06
    )、
    0.06
    Act Density 0.079%

    No Known Activations