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

    Neuronpedia

    INDEX
    Explanations

    the imperative form of the verb "be."

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

    be followed by descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rueda
    -0.46
     Nachrichten
    -0.42
    Sonntag
    -0.41
     Freitag
    -0.41
     Nilsson
    -0.41
     rapide
    -0.40
     partout
    -0.40
     Greenwood
    -0.40
     Sonntag
    -0.39
     Larson
    -0.39
    POSITIVE LOGITS
    Be
    2.00
     Be
    1.96
     BE
    1.06
    be
    1.04
    BE
    1.02
    NotBe
    0.96
     beryllium
    0.85
    ToBe
    0.84
    toBe
    0.84
     Bé
    0.81
    Act Density 0.011%

    No Known Activations