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

    Neuronpedia

    INDEX
    Explanations

    definitions and reports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     från
    0.43
     budding
    0.42
     dari
    0.42
     icin
    0.41
     Utilizing
    0.41
     pcs
    0.40
     the
    0.40
     upon
    0.40
     Doctors
    0.39
     from
    0.39
    POSITIVE LOGITS
     и
    0.46
     안정
    0.42
    reliability
    0.42
     আৰু
    0.40
     ແລະ
    0.40
     และ
    0.39
     និង
    0.38
     आणि
    0.38
     ಮತ್ತು
    0.38
     અને
    0.38
    Act Density 0.006%

    No Known Activations