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

    Neuronpedia

    INDEX
    Explanations

    health and purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lad
    0.31
    lad
    0.30
    жность
    0.29
    uale
    0.29
     Marcel
    0.29
     bec
    0.28
    Lors
    0.28
    Celula
    0.28
    Der
    0.28
     گر
    0.27
    POSITIVE LOGITS
     innocuous
    0.28
    immune
    0.27
    肯定是
    0.26
    abeled
    0.25
     pulsed
    0.25
    expanded
    0.25
     osteoarthritis
    0.24
     traceable
    0.24
     augmented
    0.23
    を通
    0.23
    Act Density 0.345%

    No Known Activations