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

    Neuronpedia

    INDEX
    Explanations

    multiple pathways/options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    paths
    -0.77
     paths
    -0.75
    Paths
    -0.58
     pathways
    -0.56
     alleys
    -0.56
    <bos>
    -0.55
     classrooms
    -0.50
    flows
    -0.50
     caminhos
    -0.50
    walls
    -0.50
    POSITIVE LOGITS
     MainAxisSize
    0.76
     propOrder
    0.69
     CreateTagHelper
    0.65
    ]")]
    0.64
    enderror
    0.57
    Xna
    0.57
     kasarigan
    0.56
    elemField
    0.56
    kär
    0.54
     समीक्षक
    0.54
    Act Density 0.066%

    No Known Activations