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

    Neuronpedia

    INDEX
    Explanations

    c

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ax
    -0.08
     precautions
    -0.07
    .xy
    -0.07
     lakh
    -0.07
    /div
    -0.06
    (num
    -0.06
    Padding
    -0.06
    िछ
    -0.06
     Tob
    -0.06
     robots
    -0.06
    POSITIVE LOGITS
    家族
    0.07
     لها
    0.07
     соци
    0.07
    akedirs
    0.07
    ?>
↵
    0.07
     prosecution
    0.06
     Reflection
    0.06
     sovereignty
    0.06
    价格
    0.06
    _ram
    0.06
    Act Density 0.003%

    No Known Activations