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

    Neuronpedia

    INDEX
    Explanations

    character conversion for each

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nější
    0.45
    =","><
    0.44
    ův
    0.43
    nitř
    0.43
    徙
    0.43
    Chaer
    0.41
     τρο
    0.40
    त्म
    0.40
     крово
    0.40
    RENCE
    0.40
    POSITIVE LOGITS
     each
    0.80
     каждого
    0.70
     каждое
    0.62
     fiecare
    0.61
     каждом
    0.59
     EACH
    0.59
     każde
    0.59
     каждым
    0.58
     every
    0.58
     каждый
    0.57
    Act Density 0.039%

    No Known Activations