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

    Neuronpedia

    INDEX
    Explanations

    tree

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     गए
    -0.07
    leveland
    -0.06
    ряду
    -0.06
    (priv
    -0.06
     نیروی
    -0.06
     مقام
    -0.06
    �
    -0.06
     تومان
    -0.06
     Charg
    -0.06
     Interface
    -0.06
    POSITIVE LOGITS
    .JsonProperty
    0.07
    )._
    0.07
    ango
    0.07
     Sheffield
    0.06
     Horizon
    0.06
     Obst
    0.06
     carousel
    0.06
    llll
    0.06
    .TextEdit
    0.06
    -с
    0.06
    Act Density 0.014%

    No Known Activations