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

    Neuronpedia

    INDEX
    Explanations

    inheritance and raw

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     రోజు
    0.50
    ্ধ্য
    0.49
     Utilisez
    0.46
    }^{+}+
    0.46
     Балтбет
    0.46
    ichia
    0.45
     继续
    0.44
     માં
    0.44
     結婚
    0.44
     Daftar
    0.44
    POSITIVE LOGITS
    Scholar
    0.48
    Diethyl
    0.43
     assin
    0.41
     predominant
    0.41
    גע
    0.41
     formative
    0.40
     outwards
    0.40
     abusive
    0.40
     xen
    0.39
    ھار
    0.39
    Act Density 0.002%

    No Known Activations