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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blur
    -0.07
     hsv
    -0.07
    566
    -0.06
    _duplicates
    -0.06
     mys
    -0.06
     lat
    -0.06
    イス
    -0.06
    Fully
    -0.06
    clipse
    -0.06
    Distance
    -0.06
    POSITIVE LOGITS
    -A
    0.07
    ]-$
    0.07
    _R
    0.07
     غذ
    0.06
    ΗΝ
    0.06
    _BACKEND
    0.06
     develop
    0.06
    鹿
    0.06
     aspir
    0.06
     While
    0.06
    Act Density 0.005%

    No Known Activations