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

    Neuronpedia

    INDEX
    Explanations

    causes or results in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    あるいは
    0.73
    または
    0.72
     Dabei
    0.71
    டியாக
    0.70
    SIGNED
    0.69
    ritt
    0.68
     तपाई
    0.67
    如果是
    0.66
     তুমি
    0.66
    或
    0.64
    POSITIVE LOGITS
     makes
    2.15
     lends
    1.88
     make
    1.87
     делает
    1.86
    makes
    1.74
     делают
    1.70
     ensures
    1.69
     contributes
    1.69
     Makes
    1.69
     means
    1.66
    Act Density 0.256%

    No Known Activations