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

    Neuronpedia

    INDEX
    Explanations

    builder pattern code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    કની
    0.39
    കി
    0.38
     العق
    0.38
     embodied
    0.37
    ihydro
    0.37
    ابية
    0.36
    🗽
    0.35
    AsUp
    0.34
     imaged
    0.34
    ियस
    0.34
    POSITIVE LOGITS
     build
    0.71
     builds
    0.68
     Build
    0.67
    build
    0.65
    Build
    0.61
     Builds
    0.52
     built
    0.51
    built
    0.49
    构建
    0.47
    building
    0.46
    Act Density 0.001%

    No Known Activations