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

    Neuronpedia

    INDEX
    Explanations

    left fence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    1.11
    د
    1.05
    2
    1.02
    8
    1.02
    4
    0.99
    র
    0.98
    д
    0.97
    л
    0.95
    𝚋
    0.94
    дят
    0.94
    POSITIVE LOGITS
    us
    1.32
    ach
    1.13
    ang
    1.12
    is
    1.08
    n
    1.05
    uje
    1.05
    uh
    1.03
    a
    1.02
    1.01
    ت
    1.01
    Act Density 0.000%

    No Known Activations