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

    Neuronpedia

    INDEX
    Explanations

    optional commercial scan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     falam
    0.92
     знают
    0.89
     irão
    0.89
     требуют
    0.88
    iscono
    0.86
     считают
    0.86
     우리
    0.85
    に加え
    0.84
     становятся
    0.84
     janë
    0.83
    POSITIVE LOGITS
     Communion
    0.80
     Chairman
    0.77
     Gift
    0.75
     écailles
    0.74
     Prepared
    0.72
     Communism
    0.70
     Pending
    0.67
     Perseverance
    0.66
    崛
    0.66
     Casi
    0.65
    Act Density 0.000%

    No Known Activations