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

    Neuronpedia

    INDEX
    Explanations

    UnityEngine C# code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikipedia
    0.47
     Wikipédia
    0.47
    Beyblade
    0.46
     contrô
    0.45
     wikipedia
    0.44
     Topological
    0.44
     Template
    0.44
    Mag
    0.43
    颢
    0.43
    ṇ
    0.42
    POSITIVE LOGITS
    입
    0.52
    치
    0.52
    ك
    0.49
     exigir
    0.47
    개
    0.46
    ام
    0.45
    우
    0.45
    정
    0.45
    هم
    0.44
    Ы
    0.44
    Act Density 0.005%

    No Known Activations