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

    Neuronpedia

    INDEX
    Explanations

    vo, info, controller, vk, gui

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्स
    1.67
    AY
    1.66
    ب
    1.63
    ের
    1.58
    s
    1.52
    한
    1.51
    ю
    1.50
    ς
    1.47
    hai
    1.45
    री
    1.41
    POSITIVE LOGITS
    ה
    1.52
    শ্রুতি
    1.48
     sebenarnya
    1.47
    트워크
    1.45
    aunque
    1.43
    ções
    1.42
    neſs
    1.40
    stoffe
    1.39
    ینګ
    1.37
    an
    1.36
    Act Density 0.001%

    No Known Activations