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

    Neuronpedia

    INDEX
    Explanations

    nitric acid, Lenovo LOQ, no touching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DI
    0.40
     उड़ान
    0.39
    DI
    0.38
     puncak
    0.38
    Ren
    0.38
     DIO
    0.38
     Di
    0.38
     D
    0.38
     Reservation
    0.38
    ToCheck
    0.38
    POSITIVE LOGITS
    稍微
    0.45
     transcend
    0.43
    пов
    0.40
     Jews
    0.39
     structurally
    0.39
     করোনাভাই
    0.39
     slightly
    0.39
     rarer
    0.38
     somewhat
    0.38
     Mathe
    0.38
    Act Density 0.000%

    No Known Activations