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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possibility or conditional scenarios

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

    preceding "be," "have," or past tense verbs

    np_acts-logits-general · gemini-2.0-flash

    possibility, potential, or uncertainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    بوابة
    -0.65
    StructEnd
    -0.59
    contentLoaded
    -0.54
    ftra
    -0.52
    diac
    -0.52
    ifel
    -0.51
    bootstrapcdn
    -0.50
    toHave
    -0.49
    gameserver
    -0.45
     fronte
    -0.45
    POSITIVE LOGITS
     could
    1.21
    could
    1.12
     conceivably
    1.11
     equally
    1.02
    Could
    1.01
     Could
    0.95
     COULD
    0.91
     equivalently
    0.88
     könnte
    0.87
     poderia
    0.84
    Act Density 0.264%

    No Known Activations