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

    Neuronpedia

    INDEX
    Explanations

    making decisions and inferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     አይደ
    0.47
    Notre
    0.45
    ཐ
    0.42
    ]');
    0.42
     Normdatei
    0.41
    で開催
    0.41
    Moles
    0.40
    ம்
    0.38
    Aug
    0.38
    Maur
    0.38
    POSITIVE LOGITS
     comparisons
    0.49
    评价
    0.47
     decipher
    0.44
     FLASH
    0.43
    aysa
    0.43
     COMPAR
    0.42
    awar
    0.42
     decoding
    0.42
     slashing
    0.42
    評
    0.41
    Act Density 0.002%

    No Known Activations