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

    Neuronpedia

    INDEX
    Explanations

    quantities and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نا
    0.53
     Fach
    0.47
     ganh
    0.46
     শহর
    0.45
     Onc
    0.45
    gebied
    0.44
     ponencia
    0.43
     lijst
    0.43
    nahi
    0.43
    CITY
    0.43
    POSITIVE LOGITS
    pped
    0.45
     shreds
    0.41
    ారె
    0.39
    很少
    0.38
     scoops
    0.38
    ␮
    0.37
     deduction
    0.37
     بهترین
    0.37
    hed
    0.36
     drifts
    0.36
    Act Density 0.002%

    No Known Activations