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

    Neuronpedia

    INDEX
    Explanations

    Time or boundaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    awtextra
    -0.74
     Period
    -0.71
    <bos>
    -0.65
    ImageContext
    -0.57
    InitVars
    -0.57
     genoux
    -0.55
     '\\;'
    -0.55
     Vikipedi
    -0.54
     Normdatei
    -0.54
    didSet
    -0.53
    POSITIVE LOGITS
    قایناقلار
    0.50
     lotto
    0.50
     copyrights
    0.49
     clearances
    0.48
     houses
    0.48
    featureID
    0.47
    Metals
    0.47
     blouses
    0.47
     masses
    0.46
     speeches
    0.46
    Act Density 0.748%

    No Known Activations