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

    Neuronpedia

    INDEX
    Explanations

    exactness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    weiler
    0.41
     মজুমদার
    0.37
    क्लो
    0.37
    etsu
    0.36
    乙
    0.35
    ুরী
    0.35
    ulum
    0.35
     Rollins
    0.35
    тров
    0.34
    ="..\
    0.34
    POSITIVE LOGITS
    Exact
    0.57
     exact
    0.48
     Exact
    0.47
    exact
    0.46
     dokład
    0.43
     precies
    0.42
     EXACT
    0.41
    prec
    0.41
     genau
    0.40
     doubling
    0.40
    Act Density 0.000%

    No Known Activations