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

    Neuronpedia

    INDEX
    Explanations

    minimizing something negative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    1.45
    s
    1.13
    大
    1.13
    ο
    1.04
    más
    0.96
     axons
    0.95
     Tử
    0.93
     impediments
    0.92
     lipoproteins
    0.90
     isotherms
    0.90
    POSITIVE LOGITS
    .
    1.38
     minimize
    1.21
    ו
    1.18
    at
    1.13
    ம்
    1.05
    AN
    0.96
     minimise
    0.95
    AT
    0.95
    ла
    0.92
     minimizar
    0.92
    Act Density 0.022%

    No Known Activations