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

    Neuronpedia

    INDEX
    Explanations

    (-

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -win
    -0.07
    /category
    -0.07
     Scaffold
    -0.07
     caller
    -0.06
    _CONTROLLER
    -0.06
     lamp
    -0.06
    ██
    -0.06
     GmbH
    -0.06
    ████
    -0.06
     Embed
    -0.06
    POSITIVE LOGITS
    _sa
    0.06
    ů
    0.06
     دانلود
    0.06
    �断
    0.06
     والس
    0.06
     Connie
    0.06
    inos
    0.06
    ...
    0.06
     фут
    0.06
    μήμα
    0.06
    Act Density 0.002%

    No Known Activations