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

    Neuronpedia

    INDEX
    Explanations

    please

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Variables
    -0.06
     multiplication
    -0.06
     scaling
    -0.06
     Tag
    -0.06
     lug
    -0.06
     Wiring
    -0.06
     Nx
    -0.06
     assignment
    -0.06
    _per
    -0.06
    Package
    -0.06
    POSITIVE LOGITS
    /csv
    0.07
     vyu
    0.07
     tất
    0.06
     kaynağı
    0.06
     DataColumn
    0.06
    -spinner
    0.06
     traged
    0.06
    Jose
    0.06
    리의
    0.06
    福利
    0.06
    Act Density 0.020%

    No Known Activations