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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to legal terminology and arguments

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

    preceding or meaning "cannot"

    np_acts-logits-general · gemini-2.0-flash

    cannot do or impossible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.51
     hjemme
    -0.47
    
    -0.47
     adequacy
    -0.46
    Ārējās
    -0.43
     tarko
    -0.43
    .*")]
    -0.42
     douceur
    -0.42
    Spare
    -0.42
     estacionamiento
    -0.41
    POSITIVE LOGITS
     cannot
    2.62
    cannot
    2.44
     Cannot
    2.38
    Cannot
    2.22
     CANNOT
    2.03
     cant
    1.99
     couldn
    1.94
     unable
    1.88
     impossibility
    1.84
     impossible
    1.78
    Act Density 0.781%

    No Known Activations