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

    Neuronpedia

    INDEX
    Explanations

    want

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of “want” (particularly in “want to”), i.e. expressions of desire or intended action.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     봉
    -0.07
    Buzz
    -0.07
    mic
    -0.06
     benz
    -0.06
    fullscreen
    -0.06
    ml
    -0.06
    .Movie
    -0.06
    ُل
    -0.06
    佐
    -0.06
    /themes
    -0.06
    POSITIVE LOGITS
    \C
    0.07
    'ils
    0.07
     intimidate
    0.06
    ENCIL
    0.06
    >",↵
    0.06
     reducers
    0.06
    阪
    0.06
    ìm
    0.06
     clashed
    0.06
     lique
    0.06
    Act Density 0.036%

    No Known Activations