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

    Neuronpedia

    INDEX
    Explanations

    news

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disrespectful
    -0.08
    Rs
    -0.07
    Router
    -0.07
    解读
    -0.07
     estimating
    -0.07
    hash
    -0.07
    resolver
    -0.06
    Tr
    -0.06
     calculator
    -0.06
     exercising
    -0.06
    POSITIVE LOGITS
    פיל
    0.09
    গ
    0.07
     shoppers
    0.07
     Broadway
    0.07
    .COMP
    0.07
    饱
    0.06
     побед
    0.06
    螠
    0.06
    מות
    0.06
    擒
    0.06
    Act Density 0.006%

    No Known Activations