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

    Neuronpedia

    INDEX
    Explanations

    political tension intrigue corruption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    1.65
    Atlet
    1.56
    }$.
    1.55
    து
    1.50
    ного
    1.46
    ğı
    1.45
    ний
    1.41
    }{
    1.38
    1
    1.38
    }$,
    1.38
    POSITIVE LOGITS
     étrang
    1.65
    iname
    1.51
    靂
    1.49
    দিনই
    1.48
     Secara
    1.45
    ي
    1.43
    ли
    1.41
    ettiin
    1.39
    ynomial
    1.38
    నిక
    1.38
    Act Density 0.024%

    No Known Activations