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

    Neuronpedia

    INDEX
    Explanations

    sitting upright

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     motionless
    0.95
     lifeless
    0.91
     idle
    0.80
     inertia
    0.76
    idle
    0.76
     Idle
    0.75
    Idle
    0.74
    ponible
    0.73
     opposite
    0.71
    惰
    0.71
    POSITIVE LOGITS
    twice
    0.76
     segmentation
    0.76
     উঠে
    0.74
     recur
    0.73
     Twice
    0.71
     seg
    0.69
     tieto
    0.69
     despi
    0.68
     கூட்டு
    0.67
     দিনে
    0.67
    Act Density 0.016%

    No Known Activations