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

    Neuronpedia

    INDEX
    Explanations

    unlimited, many, any

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     certains
    0.53
     ciertos
    0.49
     something
    0.48
     কিছুটা
    0.48
     certain
    0.47
     manches
    0.45
     aner
    0.45
     certos
    0.44
    某些
    0.43
     Certains
    0.43
    POSITIVE LOGITS
     unlimited
    1.27
    Unlimited
    1.13
     Unlimited
    1.02
     dowol
    1.00
     limitless
    0.98
     сколько
    0.92
     indefinitely
    0.89
    无限
    0.86
     любые
    0.85
     любого
    0.84
    Act Density 0.104%

    No Known Activations