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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clot
    -0.07
     البر
    -0.06
    uvo
    -0.06
     alliances
    -0.06
    ília
    -0.06
    lín
    -0.06
     власності
    -0.06
     initializes
    -0.06
    vron
    -0.06
    गल
    -0.06
    POSITIVE LOGITS
    !',↵
    0.07
     Cookies
    0.06
    :${
    0.06
    Unfortunately
    0.06
    ":
    0.06
    <small
    0.06
     herr
    0.06
    ...</
    0.06
    			↵↵
    0.06
    .onClick
    0.06
    Act Density 0.000%

    No Known Activations