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

    Neuronpedia

    INDEX
    Explanations

    German descriptive words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     לא
    0.91
     hấp
    0.87
     rec
    0.86
     רו
    0.84
     מו
    0.84
     rê
    0.83
     hind
    0.83
     χα
    0.82
     mod
    0.82
     perl
    0.82
    POSITIVE LOGITS
    wie
    0.97
     Like
    0.96
    سی
    0.92
     مثل
    0.92
    طرف
    0.90
    لون
    0.88
    مثل
    0.87
    as
    0.85
    сол
    0.83
     Ciencias
    0.83
    Act Density 0.000%

    No Known Activations