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

    Neuronpedia

    INDEX
    Explanations

    ? and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ទុក
    0.45
     recogida
    0.44
     Richt
    0.43
    讧
    0.40
     الشخص
    0.38
     depressing
    0.37
     circulaire
    0.37
    ரிக
    0.37
    除此之外
    0.36
    胯
    0.36
    POSITIVE LOGITS
    .??
    0.63
     ????
    0.57
     ?
    0.57
     ??
    0.57
    ‍♀️
    0.54
    ????
    0.53
    stanbul
    0.52
    .?
    0.50
     ???
    0.50
    ????????
    0.50
    Act Density 0.001%

    No Known Activations