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

    Neuronpedia

    INDEX
    Explanations

    I cannot browse the web

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.53
    lr
    0.52
    s
    0.51
    a
    0.51
     n
    0.50
    air
    0.49
     gift
    0.48
    ship
    0.48
     C
    0.48
     friends
    0.48
    POSITIVE LOGITS
    Saya
    0.60
    Tôi
    0.59
     ನಾನು
    0.59
    我就
    0.58
    raina
    0.51
    WITT
    0.48
    Panasonic
    0.48
     tôi
    0.47
    Biblioteca
    0.46
     Tôi
    0.46
    Act Density 0.001%

    No Known Activations