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

    Neuronpedia

    INDEX
    Explanations

    Microsoft software and file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    c
    1.30
    ка
    1.27
    in
    1.16
     In
    1.06
     Texas
    1.03
    1
    0.99
    Ç
    0.94
     tetrach
    0.91
    2
    0.91
    ka
    0.90
    POSITIVE LOGITS
    trashItem
    1.19
    জ্জিত
    1.15
    Ꮂ
    1.14
    ancel
    1.08
    永远
    1.07
     funktioniert
    1.07
     geli
    1.05
    ătoare
    1.05
    ội
    1.04
    }\!\
    1.04
    Act Density 0.705%

    No Known Activations