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

    Neuronpedia

    INDEX
    Explanations

    project name or key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    1.07
    व
    0.83
     τρόπο
    0.80
    ø
    0.79
    ž
    0.77
    รับ
    0.77
    𝚊
    0.76
     دیا۔
    0.75
    。,
    0.75
    ी
    0.75
    POSITIVE LOGITS
    s
    1.21
    c
    0.92
    m
    0.82
    কে
    0.77
    kha
    0.72
    y
    0.72
    cape
    0.70
    ς
    0.70
     maestros
    0.68
    sman
    0.67
    Act Density 0.000%

    No Known Activations