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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be"

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

    will be + past participle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chrétien
    -0.54
     parís
    -0.40
     noël
    -0.40
     jurisdic
    -0.39
     maquin
    -0.37
     froide
    -0.36
    ☼
    -0.36
    lineEdit
    -0.36
     Stö
    -0.36
     søndag
    -0.35
    POSITIVE LOGITS
     be
    1.20
     бъдат
    0.82
     shouldBe
    0.81
     been
    0.76
     бъде
    0.76
     serão
    0.76
    Será
    0.75
     able
    0.72
     Be
    0.72
    be
    0.71
    Act Density 0.079%

    No Known Activations