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

    Neuronpedia

    INDEX
    Explanations

    can help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    0.51
    اط
    0.49
    U
    0.46
    的其他
    0.44
    ೋ
    0.42
    𝐮
    0.42
    IDEA
    0.42
    ZW
    0.41
    اف
    0.41
    үл
    0.41
    POSITIVE LOGITS
    kara
    0.50
    vá
    0.48
    ᐈ
    0.48
     mesmerizing
    0.48
    ín
    0.46
     volv
    0.46
     exorbit
    0.45
     воспользоваться
    0.45
     realizar
    0.45
     incid
    0.45
    Act Density 0.006%

    No Known Activations