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

    Neuronpedia

    INDEX
    Explanations

    on the edge of locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Areas
    0.51
    Regions
    0.47
     Areas
    0.47
    areas
    0.44
    regions
    0.44
     областях
    0.42
     areas
    0.41
     regions
    0.41
     क्षेत्रों
    0.41
     AREAS
    0.40
    POSITIVE LOGITS
     opposite
    0.65
     stil
    0.64
     outskirts
    0.59
     противополо
    0.55
     hillside
    0.54
     shores
    0.52
    stil
    0.47
     Opposite
    0.47
     slopes
    0.46
    opposite
    0.46
    Act Density 0.013%

    No Known Activations