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

    Neuronpedia

    INDEX
    Explanations

    must-have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ين
    1.44
    w
    1.38
    n
    1.34
    q
    1.27
    ő
    1.26
    ال
    1.23
    ่
    1.20
    ás
    1.16
    ർ
    1.14
    ized
    1.13
    POSITIVE LOGITS
    ↵
    1.23
    рила
    0.91
     ต้อง
    0.88
    },
    0.88
     for
    0.86
     た
    0.86
    рів
    0.85
     cambiamento
    0.84
     (
    0.83
     quinto
    0.82
    Act Density 0.032%

    No Known Activations