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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     melalui
    -0.08
     plenamente
    -0.07
     indien
    -0.07
     através
    -0.07
     zitten
    -0.07
    习
    -0.07
     contender
    -0.07
    统
    -0.07
     fortress
    -0.07
     соз
    -0.07
    POSITIVE LOGITS
    ״
    0.08
     разб
    0.08
    verkehr
    0.08
    char
    0.08
     escorte
    0.08
    fahrer
    0.08
     manipulated
    0.08
    <Car
    0.08
     Chauff
    0.08
    .car
    0.08
    Act Density 0.000%

    No Known Activations