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

    Neuronpedia

    INDEX
    Explanations

    object/material names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ید
    0.71
    ным
    0.70
    ні
    0.69
    ۰
    0.64
    isierung
    0.61
    ۔
    0.61
    ling
    0.58
    has
    0.57
    ında
    0.57
     morning
    0.56
    POSITIVE LOGITS
    :
    0.87
    𝙉
    0.70
    𝙄
    0.69
    助于
    0.68
    ，
    0.68
    К
    0.68
    ،
    0.67
    Jw
    0.65
     que
    0.64
    ၊
    0.64
    Act Density 0.033%

    No Known Activations