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

    Neuronpedia

    INDEX
    Explanations

    LLM names and libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    1.09
    Re
    1.01
    N
    0.92
    Ре
    0.92
    -
    0.90
    હ
    0.89
     seconds
    0.86
    Roy
    0.86
    ffle
    0.86
     pricing
    0.84
    POSITIVE LOGITS
    s
    1.37
    ों
    1.29
    ের
    1.27
    ัตว์
    1.18
    sächlich
    1.16
    าน
    1.15
    らは
    1.15
    ўні
    1.13
    以外
    1.09
    ς
    1.07
    Act Density 0.337%

    No Known Activations