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

    Neuronpedia

    INDEX
    Explanations

    pronoun and verb combinations, especially 'it is/it's'.

    oai_token-act-pair · gemini-2.0-flash

    it

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defStyleAttr
    -0.48
     aggiun
    -0.46
     Dijo
    -0.46
    selectBy
    -0.45
     appartamento
    -0.44
     @"
    -0.42
     buoni
    -0.41
    GEBURTS
    -0.41
    ाई
    -0.40
     knows
    -0.40
    POSITIVE LOGITS
    TagMode
    0.88
     فريبيس
    0.75
    <bos>
    0.74
     nakalista
    0.74
     '\\;'
    0.70
    MLLoader
    0.69
    reportWebVitals
    0.61
    expandindo
    0.59
     BoxDecoration
    0.59
    SourceChecksum
    0.59
    Act Density 0.445%

    No Known Activations