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

    Neuronpedia

    INDEX
    Explanations

    during or until

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    无需
    0.36
    無需
    0.35
    ಙ
    0.35
     Proz
    0.34
     gê
    0.33
    觉得
    0.33
    णुओं
    0.33
     använd
    0.32
     höhere
    0.32
    قتص
    0.32
    POSITIVE LOGITS
     during
    0.82
     протягом
    0.81
     durante
    0.77
    during
    0.69
     until
    0.63
     During
    0.63
     لمدة
    0.63
     durant
    0.62
    until
    0.60
    During
    0.59
    Act Density 0.199%

    No Known Activations