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

    Neuronpedia

    INDEX
    Explanations

    urls containing .org or usa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.28
    3
    0.28
    =");
    0.27
    4
    0.25
    ariums
    0.25
    /');
    0.24
    /')
    0.24
    Markets
    0.24
    isotope
    0.24
    weile
    0.24
    POSITIVE LOGITS
    ۔
    0.33
    ”、
    0.32
    )،
    0.31
    。
    0.31
    )
    0.31
    ;
    0.30
    ።
    0.30
    )、
    0.29
    ।
    0.28
    ،
    0.27
    Act Density 0.421%

    No Known Activations