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

    Neuronpedia

    INDEX
    Explanations

    percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ۹
    0.99
     ৯
    0.97
     ninety
    0.88
     ९
    0.88
    ９
    0.85
    9
    0.84
     девя
    0.84
     Ninety
    0.82
     नाइन
    0.80
    ۹
    0.79
    POSITIVE LOGITS
     subsided
    0.39
     operativo
    0.38
    éricos
    0.36
    рті
    0.35
    璽
    0.35
    prone
    0.34
     شە
    0.33
    cmp
    0.32
    Elder
    0.31
     રચ
    0.31
    Act Density 0.052%

    No Known Activations