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

    Neuronpedia

    INDEX
    Explanations

    android manifest permissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SECUR
    0.42
    Ծ
    0.41
     geoLocation
    0.40
     réfé
    0.40
     એપ
    0.40
    vý
    0.39
     Sensors
    0.39
     dichiar
    0.39
     ಅಧಿಕ
    0.39
     titoli
    0.39
    POSITIVE LOGITS
    yo
    0.41
     well
    0.40
     tribe
    0.39
     talent
    0.39
    Drum
    0.38
    لا
    0.38
     regret
    0.37
    KING
    0.37
    Jaw
    0.37
     keenly
    0.37
    Act Density 0.000%

    No Known Activations