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

    Neuronpedia

    INDEX
    Explanations

    Code completion and function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    reserve
    0.40
    mock
    0.39
    als
    0.38
     reserves
    0.38
    鄰
    0.38
     mock
    0.37
    addSubview
    0.36
     linens
    0.36
     mlijeka
    0.36
    妈妈
    0.35
    POSITIVE LOGITS
     contenu
    0.42
     ausgeführt
    0.41
     contenidos
    0.40
    内容
    0.39
     acciones
    0.38
    を実行
    0.38
     подробно
    0.38
     allerlei
    0.37
     вести
    0.37
     причин
    0.37
    Act Density 0.164%

    No Known Activations