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

    Neuronpedia

    INDEX
    Explanations

    countries and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addock
    0.47
    ⊡
    0.47
     medulla
    0.45
     husbandry
    0.44
     gait
    0.43
     குடி
    0.42
     prioritization
    0.42
    蜱
    0.42
    .);
    0.42
    utzen
    0.42
    POSITIVE LOGITS
     France
    0.44
    和
    0.43
     Frankreich
    0.42
     ಮತ್ತೆ
    0.42
     PS
    0.41
     ಧ
    0.40
     P
    0.39
     thả
    0.39
    AMP
    0.39
     Alemanha
    0.39
    Act Density 0.000%

    No Known Activations