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

    Neuronpedia

    INDEX
    Explanations

    addition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     healthcare
    -0.07
    rowave
    -0.07
     huyết
    -0.07
    OTTOM
    -0.07
    dbContext
    -0.07
     pubkey
    -0.07
     первую
    -0.07
    arker
    -0.07
    .to
    -0.07
    .drawText
    -0.07
    POSITIVE LOGITS
     addition
    0.12
     Nit
    0.07
    <Object
    0.07
    除
    0.07
     listen
    0.06
     assistants
    0.06
     Sheldon
    0.06
     Aff
    0.06
    ไซ
    0.06
     Although
    0.06
    Act Density 0.017%

    No Known Activations