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

    Neuronpedia

    INDEX
    Explanations

    SYSTEM diagnostic & initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inseg
    0.39
    ்
    0.38
     Smooth
    0.37
     यहां
    0.36
     aqui
    0.36
     here
    0.36
     gỗ
    0.36
     Races
    0.36
     raies
    0.36
    PI
    0.36
    POSITIVE LOGITS
    града
    0.43
     BRAD
    0.40
    鍊
    0.40
    SOLUTION
    0.39
    羿
    0.38
     hota
    0.38
    agonia
    0.38
     сила
    0.37
     Schaden
    0.36
     SSID
    0.36
    Act Density 0.000%

    No Known Activations