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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -round
    -0.07
    iliyor
    -0.07
    �
    -0.06
    ers
    -0.06
    Moder
    -0.06
     sweaty
    -0.06
     upbeat
    -0.06
    戲
    -0.06
     Roulette
    -0.06
    रण
    -0.06
    POSITIVE LOGITS
     resembling
    0.08
     Legisl
    0.07
     slices
    0.06
    _compute
    0.06
     Childhood
    0.06
    иплом
    0.06
     VERIFY
    0.06
     Hospitality
    0.06
     resembled
    0.06
    _policy
    0.06
    Act Density 0.000%

    No Known Activations