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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    åĵĪä½Ľ
    -0.39
     Harvard
    -0.38
     Boston
    -0.35
    Boston
    -0.33
    achusetts
    -0.31
    æī¿å¾·
    -0.30
     Massachusetts
    -0.30
     Cambridge
    -0.29
     Petersburg
    -0.28
    éħįæĸĻ
    -0.27
    POSITIVE LOGITS
     Saddam
    0.29
    ele
    0.26
    bal
    0.25
    çļĦåľ°
    0.25
     Ranch
    0.25
     Texans
    0.25
    å¸ĸ
    0.25
    åĩºåľŁ
    0.25
    åľ°åĿª
    0.25
     MSD
    0.24
    Act Density 0.003%

    No Known Activations