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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    information related to personal development and professional growth in the workplace.

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

    The neuron spotlights short, label-style headings or subheadings (e.g. two-word titles often followed by a colon).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    691
    -0.06
    _bo
    -0.06
    odore
    -0.06
    dragon
    -0.06
    buch
    -0.06
    655
    -0.06
    769
    -0.06
     Toilet
    -0.06
    vrier
    -0.06
     DX
    -0.06
    POSITIVE LOGITS
    وجود
    0.07
     الجن
    0.07
     Skull
    0.06
    الإنجليزية
    0.06
     wordt
    0.06
     tour
    0.06
     orang
    0.06
    卻
    0.06
     города
    0.06
    \-
    0.06
    Act Density 0.377%

    No Known Activations