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

    Neuronpedia

    INDEX
    Explanations

    performance metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    嶈
    1.23
    haman
    1.18
     metamorphic
    1.13
    hattam
    1.12
     illness
    1.07
    庸
    1.07
     MTLTexture
    1.07
    符号
    1.06
    ਤ
    1.06
    ществ
    1.05
    POSITIVE LOGITS
     kanggo
    1.11
    ø
    1.05
    ز
    1.05
    i
    0.96
     personalizar
    0.94
     době
    0.94
    toMatch
    0.92
     dacă
    0.92
    <b>
    0.92
     recomiendo
    0.92
    Act Density 0.000%

    No Known Activations