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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     외부
    -0.07
     txt
    -0.06
    /provider
    -0.06
    Cnt
    -0.06
    meni
    -0.06
     OSI
    -0.06
    몬
    -0.06
     ved
    -0.06
     pop
    -0.06
     필요
    -0.06
    POSITIVE LOGITS
    каж
    0.06
    invoices
    0.06
    babel
    0.06
    복지
    0.06
    κό
    0.06
    �
    0.06
    athom
    0.06
    Globals
    0.06
     audits
    0.06
    ョ
    0.06
    Act Density 0.008%

    No Known Activations