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

    Neuronpedia

    INDEX
    Explanations

    ype

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     *↵↵↵
    -0.07
     Clarkson
    -0.06
     DOT
    -0.06
     arou
    -0.06
    acı
    -0.06
     معنی
    -0.06
     Frog
    -0.06
     〈
    -0.06
     uh
    -0.06
     rời
    -0.06
    POSITIVE LOGITS
     Đại
    0.06
    larg
    0.06
    ope
    0.06
    calling
    0.06
     pol
    0.06
    ine
    0.06
    CLASS
    0.06
    ending
    0.06
     제
    0.06
    -line
    0.06
    Act Density 0.001%

    No Known Activations