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

    Neuronpedia

    INDEX
    Explanations

    implementing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sses
    1.41
    inputFile
    1.37
    请输入
    1.30
     kepentingan
    1.29
     изобра
    1.27
    Formatted
    1.25
     immagin
    1.25
    Packaging
    1.24
     компетен
    1.22
    ر
    1.21
    POSITIVE LOGITS
    ॉस
    1.32
    ist
    1.28
    ee
    1.19
    acija
    1.18
     chili
    1.17
    غ
    1.15
     forgot
    1.15
    ار
    1.14
    ção
    1.14
    க்கா
    1.13
    Act Density 0.021%

    No Known Activations