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

    Neuronpedia

    INDEX
    Explanations

    internal code identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Despatx
    0.37
    ctomy
    0.36
    胍
    0.36
     %``
    0.36
    ewöhn
    0.36
    艨
    0.36
     않았
    0.35
     忄
    0.35
    鸮
    0.35
    ండోత్సర్గము
    0.34
    POSITIVE LOGITS
    ia
    0.49
    ot
    0.48
    ка
    0.46
    is
    0.45
    í
    0.45
    ra
    0.44
    info
    0.44
    x
    0.44
    es
    0.44
    ها
    0.43
    Act Density 0.124%

    No Known Activations