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

    Neuronpedia

    INDEX
    Explanations

    if __name__ == "__main__":

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ton
    0.86
    เบ
    0.84
     overwhelmed
    0.76
     brochures
    0.75
     albeit
    0.74
     Nether
    0.74
     afflicted
    0.73
     slippery
    0.72
    woman
    0.71
     طی
    0.71
    POSITIVE LOGITS
    __":
    1.49
    __':
    1.37
     '__
    1.28
    ="__
    1.23
     "__
    1.21
    __:
    1.18
    ():
    1.07
    יוחד
    1.03
    _:
    1.02
     dirname
    1.02
    Act Density 0.042%

    No Known Activations