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

    Neuronpedia

    INDEX
    Explanations

    undef

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -chair
    -0.06
    quisitions
    -0.06
     GtkWidget
    -0.06
    Orange
    -0.06
    �
    -0.06
     Armor
    -0.06
    (visitor
    -0.06
     месте
    -0.06
    曜日
    -0.06
    汽车
    -0.06
    POSITIVE LOGITS
     classes
    0.07
     Family
    0.06
    Ν
    0.06
    精神
    0.06
     Presidency
    0.06
    .*;↵
    0.06
     interrupt
    0.06
    duct
    0.06
    .L
    0.06
    vide
    0.06
    Act Density 0.000%

    No Known Activations