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

    Neuronpedia

    INDEX
    Explanations

    finding tokens after 'f'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    하지만
    0.42
     ہونا
    0.41
    த்திலிருந்து
    0.41
    прав
    0.41
    ampang
    0.39
    桡
    0.39
    崚
    0.39
    бул
    0.39
    attam
    0.38
    rafos
    0.38
    POSITIVE LOGITS
     touching
    0.41
    ですね
    0.39
    ['
    0.38
     resembling
    0.37
     cleansing
    0.36
     concentrating
    0.35
    During
    0.34
    OI
    0.33
    Ij
    0.33
     endorsing
    0.33
    Act Density 0.002%

    No Known Activations