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

    Neuronpedia

    INDEX
    Explanations

    card or example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    მასრულ
    0.50
    тельные
    0.49
    ressive
    0.47
    piele
    0.46
    ฉัน
    0.46
    aglia
    0.43
    もちろん
    0.42
     neutrals
    0.42
    ashire
    0.42
    garian
    0.41
    POSITIVE LOGITS
     要
    0.50
     podrá
    0.49
     造
    0.49
    er
    0.47
     infinit
    0.47
     compone
    0.46
     sá
    0.45
    ét
    0.45
    os
    0.45
     dí
    0.45
    Act Density 0.000%

    No Known Activations