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

    Neuronpedia

    INDEX
    Explanations

    please contact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     احتجاج
    0.80
     จง
    0.72
    퀼
    0.69
     econometric
    0.69
     homosexual
    0.68
     amperes
    0.68
     verhindern
    0.68
     απαι
    0.67
     insults
    0.67
     damning
    0.66
    POSITIVE LOGITS
     reach
    2.13
    Reach
    1.98
     reaching
    1.88
     reaches
    1.86
     Reach
    1.85
    reach
    1.85
     reached
    1.84
    reaching
    1.60
    reached
    1.44
     REACH
    1.33
    Act Density 0.540%

    No Known Activations