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

    Neuronpedia

    INDEX
    Explanations

    Knowing/telling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (newUser
    -0.08
     ccp
    -0.08
    䤀
    -0.07
    컵
    -0.07
     UIAlert
    -0.07
    up
    -0.07
     beef
    -0.07
    ullets
    -0.07
    ул
    -0.07
    .snp
    -0.07
    POSITIVE LOGITS
     *(*
    0.07
     sorte
    0.07
    我妈
    0.07
     Doming
    0.07
    艺人
    0.07
    传媒
    0.07
     ngươi
    0.07
    本质上
    0.07
    据介绍
    0.07
    科室
    0.07
    Act Density 0.034%

    No Known Activations