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

    Neuronpedia

    INDEX
    Explanations

    address components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jika
    1.21
     questione
    1.18
     simpat
    1.13
    WITH
    1.11
     apag
    1.06
    чия
    1.05
     dicen
    1.05
    Dengan
    1.04
     terima
    1.03
    ovem
    1.02
    POSITIVE LOGITS
    ными
    1.11
    ing
    1.04
    ة
    1.03
    ת
    1.03
    \"");
    1.00
    ែក
    0.93
    تس
    0.93
    ণিজ
    0.93
    rän
    0.91
    staben
    0.91
    Act Density 0.000%

    No Known Activations