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

    Neuronpedia

    INDEX
    Explanations

    half a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ö
    1.21
    r
    1.09
    n
    1.01
    ü
    1.01
    rö
    1.00
    ot
    1.00
    un
    0.98
    ל
    0.96
    j
    0.95
    uc
    0.93
    POSITIVE LOGITS
     megawatts
    1.01
     twofold
    0.98
     tenfold
    0.98
     halves
    0.96
     மடங்கு
    0.95
     doubled
    0.93
     desires
    0.89
     dramatically
    0.88
     nanoparticles
    0.87
     coinc
    0.86
    Act Density 0.830%

    No Known Activations