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

    Neuronpedia

    INDEX
    Explanations

    numbers and associated quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sophisticated
    0.33
     zéro
    0.32
     audacity
    0.32
    ؟
    0.32
     dijel
    0.30
     Peki
    0.30
     sophistication
    0.30
     neler
    0.29
     Еўропы
    0.29
     analytic
    0.28
    POSITIVE LOGITS
    oc
    0.40
    ma
    0.40
    ul
    0.39
    u
    0.38
    ut
    0.38
    has
    0.37
    gly
    0.37
    ny
    0.37
    ur
    0.37
    ali
    0.37
    Act Density 0.041%

    No Known Activations