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

    Neuronpedia

    INDEX
    Explanations

    numbers, code, and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     세포
    0.54
    asjon
    0.54
     музи
    0.50
     muzy
    0.50
     Hø
    0.49
     metabolized
    0.49
    ling
    0.48
    musik
    0.48
    amura
    0.47
    ary
    0.47
    POSITIVE LOGITS
     uni
    0.53
    ++)
    0.50
     Unite
    0.50
    اده
    0.49
    ढ़ा
    0.48
    UM
    0.48
     تر
    0.47
    MOV
    0.47
     Tele
    0.46
     صورت
    0.46
    Act Density 0.000%

    No Known Activations