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

    Neuronpedia

    INDEX
    Explanations

    expressions of desire or intention

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

    "Want to" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    expressing intent or desire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.56
    routeProvider
    -0.54
    ViewChild
    -0.53
     ciutat
    -0.53
     eiland
    -0.51
     QtCore
    -0.50
    savevideo
    -0.50
    URLException
    -0.50
     hyö
    -0.49
    rophilic
    -0.49
    POSITIVE LOGITS
     ensure
    0.70
    ensure
    0.58
    ]),
    0.54
     Ensure
    0.53
     assure
    0.52
    IconModule
    0.52
     ensured
    0.52
    обе
    0.52
    mpto
    0.51
    wanza
    0.50
    Act Density 0.070%

    No Known Activations