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

    Neuronpedia

    INDEX
    Explanations

    beneath the layers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     roof
    0.93
    Roof
    0.89
     Roof
    0.86
     Cooperative
    0.82
    roof
    0.82
     banner
    0.74
    boolean
    0.72
     Guth
    0.71
     apakah
    0.69
     Surrounded
    0.69
    POSITIVE LOGITS
     layers
    1.24
     layer
    1.01
     Layers
    0.89
    では
    0.89
    boards
    0.86
     层
    0.86
    层
    0.83
    ilayer
    0.83
    layer
    0.82
    ),
    0.79
    Act Density 0.016%

    No Known Activations