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

    Neuronpedia

    INDEX
    Explanations

    code documentation and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     out
    0.53
    出る
    0.47
    out
    0.45
    出的
    0.44
    出来
    0.44
     outta
    0.42
     вышла
    0.41
    出
    0.40
     quenched
    0.40
    এক্স
    0.39
    POSITIVE LOGITS
     în
    0.45
    في
    0.43
    Axes
    0.42
    emente
    0.41
    OCUS
    0.41
     trong
    0.41
     في
    0.40
     IEnumerator
    0.40
     crop
    0.39
     in
    0.39
    Act Density 0.000%

    No Known Activations