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

    Neuronpedia

    INDEX
    Explanations

    essentially, still

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flashy
    0.49
     pliers
    0.46
    ishop
    0.45
    शीलता
    0.44
    nThe
    0.44
     හැකිය
    0.44
    讼
    0.44
     hoặc
    0.43
    是没有
    0.42
    च्छेद
    0.41
    POSITIVE LOGITS
    மல
    0.44
    وبا
    0.42
    ارد
    0.41
     prin
    0.40
     expres
    0.39
     Länder
    0.39
    문
    0.38
    pital
    0.38
    PRINC
    0.38
    ومن
    0.38
    Act Density 0.007%

    No Known Activations