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

    Neuronpedia

    INDEX
    Explanations

    options and instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lime
    -0.08
     lime
    -0.08
     помощ
    -0.07
    lit
    -0.07
    filename
    -0.07
    iful
    -0.07
     നിർമ്മ
    -0.07
     jugu
    -0.07
     மூலம்
    -0.07
     cadastro
    -0.07
    POSITIVE LOGITS
     emphasized
    0.09
    调整
    0.09
     flexibil
    0.09
     realloc
    0.09
     emphasizing
    0.09
     Allocate
    0.09
     enfat
    0.09
     emphasize
    0.09
     Adjust
    0.09
     adjusted
    0.09
    Act Density 0.036%

    No Known Activations