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

    Neuronpedia

    INDEX
    Explanations

    your [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sendiri
    0.66
    自身
    0.66
     itself
    0.64
    own
    0.57
    自身的
    0.55
     자체
    0.54
     собственных
    0.54
     खुद
    0.53
     włas
    0.52
     himself
    0.51
    POSITIVE LOGITS
     entire
    0.57
     actual
    0.42
     gesamte
    0.37
     ACTUAL
    0.37
    entire
    0.36
    Entire
    0.36
    整個
    0.36
    Actual
    0.36
     actuales
    0.34
     current
    0.34
    Act Density 0.060%

    No Known Activations