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

    Neuronpedia

    INDEX
    Explanations

    during or throughout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    のではなく
    0.21
     sobot
    0.20
     آنچه
    0.20
     کجا
    0.20
     причем
    0.20
     Gently
    0.20
    gen
    0.19
     Nachdem
    0.19
     nodig
    0.19
    нди
    0.19
    POSITIVE LOGITS
     during
    0.38
     durante
    0.37
     خلال
    0.33
     tijdens
    0.32
     podczas
    0.31
    during
    0.29
     throughout
    0.28
     DURING
    0.28
     أثناء
    0.27
     během
    0.27
    Act Density 0.354%

    No Known Activations