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

    Neuronpedia

    INDEX
    Explanations

    sitting and standing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    into
    0.87
    Into
    0.84
     Into
    0.82
     serata
    0.77
     into
    0.74
    来的
    0.70
     Depth
    0.69
    วาม
    0.69
     ايا
    0.68
    depth
    0.67
    POSITIVE LOGITS
     tall
    1.13
     idle
    1.05
     taller
    1.02
     ovation
    0.97
     tallest
    0.95
     still
    0.92
     pati
    0.88
     Tall
    0.88
     stunned
    0.85
     dậy
    0.85
    Act Density 0.061%

    No Known Activations