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

    Neuronpedia

    INDEX
    Explanations

    code and security concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ٕ
    0.38
     gymnastics
    0.38
    İŞ
    0.38
    Ñ
    0.38
    rinho
    0.38
    自動車
    0.37
    ֱ
    0.37
    RUTA
    0.37
     intravenously
    0.37
     hurling
    0.36
    POSITIVE LOGITS
     */
    0.44
     numpy
    0.41
    <unused62>
    0.39
    ')
    0.39
     \
    0.39
     json
    0.39
    ");
    0.38
     {}
    0.38
    ></
    0.38
    '):
    0.36
    Act Density 0.232%

    No Known Activations