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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "be" used in various grammatical contexts

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

    what something can be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lö
    -0.36
     toilettes
    -0.35
     compositeur
    -0.34
    tt
    -0.34
     Schmid
    -0.33
     jurisdic
    -0.32
     noël
    -0.32
     distrik
    -0.31
     maquin
    -0.30
     desapar
    -0.30
    POSITIVE LOGITS
     be
    1.08
    CanBe
    1.01
    <unused41>
    0.93
    [@BOS@]
    0.92
    <unused74>
    0.92
    <unused43>
    0.92
    <unused68>
    0.92
    <unused52>
    0.92
    <unused8>
    0.92
    <unused28>
    0.92
    Act Density 0.060%

    No Known Activations