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
     кле
    -0.07
    _CHARSET
    -0.07
     реб
    -0.06
     slicing
    -0.06
    _sc
    -0.06
    cec
    -0.06
    58
    -0.06
    _labels
    -0.06
    -CS
    -0.06
     dě
    -0.06
    POSITIVE LOGITS
     ~/
    0.08
    ("~/
    0.07
     Moon
    0.07
    ~/
    0.07
    (mark
    0.06
     nationwide
    0.06
     ContentView
    0.06
    asal
    0.06
     novel
    0.06
    죽
    0.06
    Act Density 0.001%

    No Known Activations