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

    Neuronpedia

    INDEX
    Explanations

    originates or causes development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    па
    0.87
     on
    0.82
    ти
    0.76
    nament
    0.75
    িং
    0.73
    on
    0.73
     بیاکت
    0.72
    ură
    0.68
     بیاکتنې
    0.68
    ပြည်
    0.68
    POSITIVE LOGITS
    </h3>
    0.82
     denna
    0.80
    k
    0.79
    지
    0.78
    </h2>
    0.77
     denne
    0.75
    0.75
    ش
    0.75
    H
    0.75
    어
    0.73
    Act Density 0.014%

    No Known Activations