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

    Neuronpedia

    INDEX
    Explanations

    code structure and programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     های
    0.41
    eless
    0.39
     টেলিভিশ
    0.39
     Drag
    0.38
     accusations
    0.38
     bullshit
    0.37
    rible
    0.37
     nostrils
    0.37
     Restoration
    0.36
    ައް
    0.36
    POSITIVE LOGITS
     наличие
    0.44
     наличи
    0.43
     наличии
    0.42
    0.41
    嬉
    0.40
    Ov
    0.39
    ibilité
    0.39
     downloadable
    0.39
     Currie
    0.39
    াতে
    0.39
    Act Density 0.000%

    No Known Activations