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

    Neuronpedia

    INDEX
    Explanations

    the verb "be" in various forms and contexts

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

    can be followed by a state or acted upon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rolo
    -0.42
     Rø
    -0.42
    lö
    -0.41
    rizio
    -0.40
    föl
    -0.40
    Sö
    -0.39
    guero
    -0.39
     distrik
    -0.39
     Schmid
    -0.39
    io
    -0.38
    POSITIVE LOGITS
    CanBe
    1.02
     be
    0.93
     can
    0.74
     pouvons
    0.65
     бъдат
    0.63
     bisa
    0.62
     Be
    0.62
    Puede
    0.61
    ToBe
    0.61
    ารถ
    0.60
    Act Density 0.067%

    No Known Activations