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

    Neuronpedia

    INDEX
    Explanations

    skills and personal qualities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pale
    -0.08
     eksper
    -0.08
     chilli
    -0.08
     expr
    -0.07
     شا
    -0.07
    .DATA
    -0.07
    atsen
    -0.07
     Wolfgang
    -0.07
    ूरत
    -0.07
     Pale
    -0.07
    POSITIVE LOGITS
    🏼
    0.08
    <!--
    0.08
    imp
    0.08
    cou
    0.08
    fuel
    0.08
    (Re
    0.07
    /Re
    0.07
     requisite
    0.07
    🏻
    0.07
    抜
    0.07
    Act Density 0.078%

    No Known Activations