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

    Neuronpedia

    INDEX
    Explanations

    descriptions of content

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    㤘
    -0.08
    Gift
    -0.07
    .Preference
    -0.07
    累
    -0.07
    葵
    -0.06
     isLoading
    -0.06
    NewUrlParser
    -0.06
    🍦
    -0.06
    こちら
    -0.06
     NAT
    -0.06
    POSITIVE LOGITS
    >
↵
    0.07
    .JButton
    0.06
    𝚝
    0.06
    ">
↵
    0.06
     ?>">↵
    0.06
     tav
    0.06
    不了
    0.06
    牍
    0.06
    änd
    0.06
    ánchez
    0.06
    Act Density 0.079%

    No Known Activations