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

    Neuronpedia

    INDEX
    Explanations

    numbers and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ње
    0.41
    ња
    0.40
     والأ
    0.38
    鹦
    0.38
     possam
    0.37
    ኼ
    0.37
    問題
    0.36
     berkaitan
    0.36
     ف
    0.36
    ैनल
    0.36
    POSITIVE LOGITS
    0.42
    .)
    0.40
     .)
    0.35
    oncé
    0.35
    matu
    0.34
    ဍ
    0.34
    .(
    0.34
     worldRank
    0.34
    agu
    0.34
     หา
    0.33
    Act Density 0.333%

    No Known Activations