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

    Neuronpedia

    INDEX
    Explanations

    detecting a token and its common follow-up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    0.48
    ↵↵↵↵↵↵
    0.46
    ↵↵↵↵↵
    0.44
    ↵↵↵↵
    0.44
    ↵↵↵
    0.44
    ary
    0.44
    ']
    0.43
    }{$\
    0.43
    {*
    0.42
    }{
    0.41
    POSITIVE LOGITS
    ))[
    0.43
     secciones
    0.43
    olica
    0.43
    ্নের
    0.42
    فاض
    0.42
    sections
    0.41
    ಚಿ
    0.41
     алфа
    0.40
    தைப்
    0.40
    တွင်
    0.40
    Act Density 0.000%

    No Known Activations