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

    Neuronpedia

    INDEX
    Explanations

    efficient technical descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    readLine
    0.49
    afone
    0.47
     шокола
    0.47
     उसी
    0.44
     حافظ
    0.44
    aço
    0.43
    spiration
    0.43
    axies
    0.43
    ames
    0.43
    ucket
    0.42
    POSITIVE LOGITS
    חו
    0.46
    。
    0.45
    ২
    0.45
     niest
    0.43
    فر
    0.43
    த்தம்
    0.42
     yar
    0.42
    fw
    0.41
     neuest
    0.41
     panels
    0.41
    Act Density 0.001%

    No Known Activations