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

    Neuronpedia

    INDEX
    Explanations

    comfort level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    сия
    0.46
     Müdür
    0.45
    煐
    0.44
    ℞
    0.44
    দেশিক
    0.43
     Между
    0.43
    クリック
    0.43
     ಮಂಗಳ
    0.42
     失
    0.42
    Université
    0.42
    POSITIVE LOGITS
    ade
    0.56
    ule
    0.52
    dote
    0.48
    onet
    0.46
    addi
    0.46
    èle
    0.46
    otry
    0.45
    1
    0.45
     i
    0.45
    6
    0.45
    Act Density 0.002%

    No Known Activations