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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kenyan
    0.70
     Kenya
    0.68
     confines
    0.58
     Mombasa
    0.58
     Moringa
    0.58
     Namib
    0.57
     Hence
    0.57
     acacia
    0.57
     mothers
    0.57
     Masai
    0.57
    POSITIVE LOGITS
    個
    0.58
    ende
    0.57
     ndani
    0.56
     weken
    0.56
    上に
    0.55
     mwaka
    0.54
     kwenye
    0.54
    إذا
    0.54
     mf
    0.54
    amini
    0.54
    Act Density 0.000%

    No Known Activations