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

    Neuronpedia

    INDEX
    Explanations

    Uniform Circular, configured using

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    reas
    -0.69
     hauled
    -0.68
     }}{\
    -0.68
     Conv
    -0.66
     murals
    -0.64
    isStatic
    -0.64
    sigt
    -0.64
     במקום
    -0.63
     Clustering
    -0.63
     antigens
    -0.63
    POSITIVE LOGITS
     дово
    0.75
    Looking
    0.69
    Damit
    0.67
    uku
    0.62
    gnu
    0.62
    democ
    0.61
     duyên
    0.61
    Designated
    0.61
     heißen
    0.61
     aik
    0.60
    Act Density 0.079%

    No Known Activations