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

    Neuronpedia

    INDEX
    Explanations

    N followed by specific word parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ormal
    0.69
    لومات
    0.68
     pkt
    0.65
    ज्ञ
    0.65
    ductor
    0.64
    म
    0.63
    ote
    0.62
    ভাসের
    0.62
    nym
    0.61
    umber
    0.60
    POSITIVE LOGITS
    inian
    0.84
     orth
    0.76
     hàn
    0.72
    wia
    0.70
    antic
    0.70
    ations
    0.69
     전시
    0.68
    azioni
    0.67
     order
    0.67
    ræ
    0.64
    Act Density 0.033%

    No Known Activations