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

    Neuronpedia

    INDEX
    Explanations

    Code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     meals
    -0.07
    marine
    -0.07
    TEX
    -0.07
     valued
    -0.07
     fixed
    -0.06
     distributes
    -0.06
     expans
    -0.06
    SEQU
    -0.06
     energia
    -0.06
     usuário
    -0.06
    POSITIVE LOGITS
    /'↵↵
    0.06
     typo
    0.06
    هل
    0.06
    /App
    0.06
     आत
    0.06
     setups
    0.06
    lsruhe
    0.06
    }}↵
    0.06
    -pos
    0.05
     regimen
    0.05
    Act Density 0.198%

    No Known Activations