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

    Neuronpedia

    INDEX
    Explanations

    error handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۔
    0.40
    ті
    0.38
    น้ำ
    0.38
    ના
    0.38
     are
    0.37
    ł
    0.36
    นำ
    0.36
    มัน
    0.33
    یل
    0.33
    с
    0.32
    POSITIVE LOGITS
    c
    0.48
    f
    0.40
    w
    0.39
     amend
    0.39
    h
    0.38
    n
    0.38
    8
    0.37
     allemand
    0.37
     assegn
    0.37
    ｸ
    0.37
    Act Density 0.378%

    No Known Activations