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

    Neuronpedia

    INDEX
    Explanations

    lists of abbreviations and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    З
    0.59
    리
    0.54
    பெ
    0.49
    Гу
    0.46
    ائي
    0.46
    リ
    0.45
    ？
    0.45
    。
    0.45
    {
    0.44
    攻擊
    0.44
    POSITIVE LOGITS
    Circular
    0.49
     Constitución
    0.48
     Ansari
    0.47
     Seiten
    0.46
    Indent
    0.46
     disappointment
    0.45
     Buckley
    0.43
     Langley
    0.43
     Christensen
    0.42
     Constituição
    0.41
    Act Density 0.002%

    No Known Activations