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

    Neuronpedia

    INDEX
    Explanations

    interview questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     complète
    0.52
     swabs
    0.46
    खार
    0.45
     expedi
    0.45
     oxid
    0.44
     alcalde
    0.43
     heps
    0.43
     independ
    0.42
     accompl
    0.42
     полный
    0.42
    POSITIVE LOGITS
     লিখে
    0.47
    自身
    0.46
     regained
    0.46
    语言
    0.44
     Written
    0.43
     Linguistics
    0.42
    自身的
    0.41
     sustained
    0.41
     juxtaposition
    0.41
     Namely
    0.40
    Act Density 0.021%

    No Known Activations