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 or need

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    modelBuilder
    -0.68
    k
    -0.66
    woordig
    -0.61
     Pons
    -0.61
    FACT
    -0.60
     Persons
    -0.60
    Slf
    -0.60
    ac
    -0.59
     Raton
    -0.58
    ַת
    -0.58
    POSITIVE LOGITS
     hoped
    0.94
     originalmente
    0.93
    twas
    0.88
     WANTED
    0.87
     ―――――
    0.84
     autrefois
    0.84
     '/')
    0.80
    던
    0.79
    €)
    0.79
     wished
    0.79
    Act Density 0.038%

    No Known Activations