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

    Neuronpedia

    INDEX
    Explanations

    diets and exercise

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    탕
    -0.07
    洒
    -0.07
    存量
    -0.07
    قابل
    -0.07
     $$$
    -0.07
    ="↵
    -0.07
    qd
    -0.07
     survivor
    -0.06
     Balls
    -0.06
    是最好的
    -0.06
    POSITIVE LOGITS
     QWidget
    0.07
     debates
    0.07
    Say
    0.07
    狴
    0.06
     ipt
    0.06
     bool
    0.06
    -HT
    0.06
    inaire
    0.06
     father
    0.06
    dit
    0.06
    Act Density 0.007%

    No Known Activations