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

    Neuronpedia

    INDEX
    Explanations

    URLs and website traffic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ly
    -0.54
    <bos>
    -0.52
    most
    -0.50
     most
    -0.47
    ništvo
    -0.47
    ImageContext
    -0.46
     potest
    -0.44
    ring
    -0.44
    lichkeit
    -0.43
     colonies
    -0.43
    POSITIVE LOGITS
    SourceChecksum
    0.63
     Roskov
    0.61
    PreferredItem
    0.57
    IContainer
    0.55
    source
    0.54
     GenerationType
    0.54
    ArgumentParser
    0.54
    ientôt
    0.52
    #+#
    0.52
    cardname
    0.50
    Act Density 0.157%

    No Known Activations