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

    Neuronpedia

    INDEX
    Explanations

    multi-language or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.35
    1.34
    }=\
    1.28
    Bedroom
    1.26
    ोटी
    1.21
     messed
    1.21
     ruining
    1.21
    1.20
     stereotypes
    1.19
     cultivators
    1.18
    POSITIVE LOGITS
    ある
    1.24
    ה
    1.15
    ли
    1.13
    wegian
    1.12
    ب
    1.07
    циа
    1.06
     leichte
    1.05
     Artikel
    1.05
    sept
    1.04
     Auswahl
    1.03
    Act Density 0.001%

    No Known Activations