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

    Neuronpedia

    INDEX
    Explanations

    the word "will" and other auxiliary verbs related to future tense and possibility.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /*č↵
    -0.07
    lernen
    -0.06
     kabil
    -0.06
    érique
    -0.06
    /**č↵
    -0.06
    icerca
    -0.06
     být
    -0.06
    imers
    -0.06
    Ñĸки
    -0.06
    ukkan
    -0.06
    POSITIVE LOGITS
     soon
    0.10
    Soon
    0.08
    fully
    0.08
     Soon
    0.08
     forever
    0.08
     tomorrow
    0.07
    UNUSED
    0.07
    soon
    0.07
    ow
    0.07
     Bour
    0.06
    Act Density 0.102%

    No Known Activations