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

    Neuronpedia

    INDEX
    Explanations

    DIY or building projects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     القد
    -0.88
     kuns
    -0.74
     Facility
    -0.72
     discs
    -0.71
     mécan
    -0.71
     facilities
    -0.71
     recurso
    -0.70
    俑
    -0.70
     WRITING
    -0.69
    を設定
    -0.69
    POSITIVE LOGITS
     DIY
    2.41
    DIY
    2.00
     diy
    1.86
    diy
    1.73
     build
    1.73
     builder
    1.54
    build
    1.44
     builds
    1.44
     project
    1.38
     Build
    1.38
    Act Density 0.037%

    No Known Activations