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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and expressions indicating intention or necessity

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

    vil, kan, må, skal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.47
    midler
    -0.45
    にほんブログ村
    -0.42
     Cæsar
    -0.40
     prostřed
    -0.39
     toallas
    -0.39
    stet
    -0.38
     Monfieur
    -0.38
     Wiktionnaire
    -0.37
    ově
    -0.37
    POSITIVE LOGITS
     kan
    0.97
     might
    0.66
    might
    0.61
    Kan
    0.60
     MIGHT
    0.59
     صوتيه
    0.58
     may
    0.58
    Might
    0.56
     Kan
    0.56
     podría
    0.55
    Act Density 0.001%

    No Known Activations