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

    Neuronpedia

    INDEX
    Explanations

    `import sys`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /(:
    0.45
     DAVID
    0.41
     embry
    0.40
    交易
    0.40
    \}=\
    0.38
    зации
    0.38
    DETECT
    0.38
    }/>
    0.37
    DAVID
    0.37
    垲
    0.36
    POSITIVE LOGITS
     reload
    0.47
    si
    0.45
     mush
    0.45
     Reload
    0.44
    銃
    0.42
     Lily
    0.41
     Mush
    0.41
     reloading
    0.41
     Bai
    0.40
     watered
    0.39
    Act Density 0.000%

    No Known Activations