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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    the neuron lights up on descriptive content-scope words—nouns and adjectives that outline features or instructions (e.g. “survival,” “encounters,” “detailed,” “nuanced,” “content”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ंतर
    -0.06
     пять
    -0.06
    ativ
    -0.06
     Orwell
    -0.06
    uvwxyz
    -0.06
    specifier
    -0.06
    opis
    -0.06
    _lc
    -0.06
     pars
    -0.06
     روست
    -0.06
    POSITIVE LOGITS
    バス
    0.07
    ­ing
    0.06
     ])->
    0.06
    .VisualStudio
    0.06
    ',↵↵
    0.06
     Yun
    0.06
     призначення
    0.06
     Repos
    0.06
    เขา
    0.06
    ­tion
    0.06
    Act Density 0.041%

    No Known Activations