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

    Neuronpedia

    INDEX
    Explanations

    continues to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    icle
    0.37
    ";
    0.35
     åter
    0.35
    ishes
    0.33
    ook
    0.33
    '
    0.33
     devenu
    0.33
     Knows
    0.33
     pén
    0.32
     Exception
    0.32
    POSITIVE LOGITS
     unchanged
    0.48
     continue
    0.47
     συνέχ
    0.46
    下去
    0.44
     traditions
    0.44
     쭉
    0.44
     unab
    0.43
     కొన
    0.43
     weiterhin
    0.43
     계속
    0.42
    Act Density 0.014%

    No Known Activations