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

    Neuronpedia

    INDEX
    Explanations

    left followed by hand, arm, brain, sidebar, OUT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pose
    0.43
    fc
    0.42
    hxx
    0.41
    hah
    0.41
     स्वामित्व
    0.40
    Mapper
    0.40
    族
    0.39
    編成
    0.39
    武装
    0.39
    长大
    0.39
    POSITIVE LOGITS
     wing
    0.59
     sidebar
    0.55
    wing
    0.54
    袒
    0.50
    ward
    0.49
     左
    0.48
     ventricle
    0.48
     flank
    0.48
     hemisphere
    0.48
     winger
    0.46
    Act Density 0.018%

    No Known Activations