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

    Neuronpedia

    INDEX
    Explanations

    the following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vibes
    0.94
    未知
    0.91
    weird
    0.89
    arounds
    0.84
     tricks
    0.82
     crazy
    0.81
    こういう
    0.81
     비슷
    0.81
     math
    0.80
     weird
    0.80
    POSITIVE LOGITS
     following
    1.04
     foregoing
    1.03
     United
    0.98
    United
    0.97
     undersigned
    0.93
     term
    0.92
     seguente
    0.92
     presente
    0.91
     présente
    0.91
     présentes
    0.90
    Act Density 0.216%

    No Known Activations