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

    Neuronpedia

    INDEX
    Explanations

    advice and clarification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    de
    0.47
     Nong
    0.46
    ellige
    0.45
    ному
    0.44
     সঠিক
    0.44
    ান্ত্রিক
    0.44
    कां
    0.44
    Quit
    0.43
    og
    0.42
    گی
    0.42
    POSITIVE LOGITS
     Альбер
    0.49
    ALBERT
    0.48
     стату
    0.47
     жу
    0.47
     области
    0.45
     interpreters
    0.44
    嶂
    0.44
    狧
    0.43
     invitations
    0.42
     музея
    0.42
    Act Density 0.001%

    No Known Activations