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

    Neuronpedia

    INDEX
    Explanations

    software glitches, diagnosis, California

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isEmpty
    0.50
    ре
    0.46
    Ic
    0.45
    ian
    0.44
    rer
    0.43
    men
    0.43
    res
    0.43
    treated
    0.43
    nder
    0.42
    der
    0.42
    POSITIVE LOGITS
          
    0.48
     sanctuaries
    0.48
     monetize
    0.48
     (#
    0.46
     oppression
    0.46
     total
    0.45
     solvency
    0.45
     multitasking
    0.44
     upbringing
    0.44
     clutches
    0.44
    Act Density 0.002%

    No Known Activations