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

    Neuronpedia

    INDEX
    Explanations

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amp
    0.47
    ash
    0.47
     and
    0.45
    and
    0.44
    ist
    0.43
    om
    0.42
    ard
    0.40
    ar
    0.39
    er
    0.38
    ći
    0.38
    POSITIVE LOGITS
     grotes
    0.49
     của
    0.48
    ນ
    0.48
     unor
    0.47
    ग्वि
    0.45
     convivial
    0.43
    Н
    0.43
    सच
    0.43
     trưng
    0.42
     categor
    0.42
    Act Density 1.651%

    No Known Activations