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

    Neuronpedia

    INDEX
    Explanations

    Technical diagrams with part numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     نخست
    -0.08
     bridge
    -0.07
     abst
    -0.07
    fre
    -0.07
     chimpan
    -0.07
     Movies
    -0.07
     eject
    -0.06
     continuous
    -0.06
    uts
    -0.06
     사회
    -0.06
    POSITIVE LOGITS
    \↵
    0.07
    >";↵↵
    0.06
    (chalk
    0.06
    atLng
    0.06
    _Label
    0.06
    ，↵↵
    0.06
    """↵↵↵
    0.06
    updating
    0.06
    ographics
    0.06
    لسل
    0.06
    Act Density 0.066%

    No Known Activations