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

    Neuronpedia

    INDEX
    Explanations

    bootstrap container and classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bella
    0.39
     Parte
    0.38
     segunda
    0.36
     second
    0.36
     slit
    0.35
     corrupted
    0.34
     actual
    0.34
     damaged
    0.33
     messed
    0.33
    с
    0.33
    POSITIVE LOGITS
    容器
    0.47
    container
    0.45
     контей
    0.44
     कंटे
    0.42
     Container
    0.40
     Containers
    0.40
     container
    0.40
    glyphicon
    0.40
    clearfix
    0.40
    مركز
    0.39
    Act Density 0.006%

    No Known Activations