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

    Neuronpedia

    INDEX
    Explanations

    Geographic locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     loafers
    0.37
     gap
    0.35
    ការព
    0.35
     priming
    0.33
     miso
    0.33
     bondage
    0.33
    ാൻഡ്
    0.32
     pecados
    0.32
    mW
    0.32
     ivvu
    0.31
    POSITIVE LOGITS
     США
    0.73
     USA
    0.66
     Germany
    0.61
     ประเทศ
    0.61
    Germany
    0.58
    ،
    0.55
     Switzerland
    0.54
    日本では
    0.53
     Alemanha
    0.52
     Indonesia
    0.52
    Act Density 0.023%

    No Known Activations