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

    Neuronpedia

    INDEX
    Explanations

    internet text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     чув
    -0.06
     breastfeeding
    -0.06
     rud
    -0.06
     emphasized
    -0.06
     infancy
    -0.06
     vague
    -0.06
     naprost
    -0.06
    "..
    -0.06
     fron
    -0.06
     dmg
    -0.06
    POSITIVE LOGITS
    graphql
    0.07
    parable
    0.06
    IR
    0.06
    letion
    0.06
     appeal
    0.06
    actory
    0.06
    pageSize
    0.06
    cntl
    0.06
     leased
    0.06
    攻撃
    0.06
    Act Density 0.000%

    No Known Activations