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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or potential consequences

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

    may be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.54
     przekon
    -0.44
     hieß
    -0.44
     bestäm
    -0.44
     nadzie
    -0.43
     gärna
    -0.43
    perhaps
    -0.43
     perhaps
    -0.42
     varandra
    -0.42
     sekal
    -0.42
    POSITIVE LOGITS
     cause
    0.59
    GEBURTSDATUM
    0.52
     AssemblyCulture
    0.52
     ब्रेकडाउन
    0.50
    ɵɵ
    0.49
    cause
    0.48
     harm
    0.48
     doInBackground
    0.47
    makeText
    0.47
    WebElementEntity
    0.45
    Act Density 0.009%

    No Known Activations