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

    Neuronpedia

    INDEX
    Explanations

    bow/rainbow

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     produto
    -0.07
     concentrate
    -0.06
     chassis
    -0.06
    弃
    -0.06
    validators
    -0.06
     pronunciation
    -0.06
     Wrest
    -0.06
     gắng
    -0.06
    508
    -0.06
    >c
    -0.06
    POSITIVE LOGITS
     Puppy
    0.07
    emie
    0.07
    0.07
    �ng
    0.07
     五
    0.06
    _MIN
    0.06
    UCH
    0.06
     roulette
    0.06
     impair
    0.06
    )})
    0.06
    Act Density 0.002%

    No Known Activations