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

    Neuronpedia

    INDEX
    Explanations

    is known as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    벽
    1.21
    ので
    1.17
    ☜
    1.17
     vows
    1.15
     불구하고
    1.15
    ھی
    1.14
    しく
    1.14
     nus
    1.12
    el
    1.10
    मेंट
    1.09
    POSITIVE LOGITS
    s
    2.42
    ের
    1.95
    ات
    1.90
    ों
    1.56
    sah
    1.49
    ים
    1.48
    sman
    1.44
    sala
    1.35
    sas
    1.34
    sop
    1.31
    Act Density 0.000%

    No Known Activations