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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    photobucket
    -0.58
    ükemmel
    -0.54
     estekak
    -0.54
     vuitton
    -0.51
    XmlAccessType
    -0.51
     SimpleName
    -0.48
     shot
    -0.47
    ladel
    -0.46
     незавершена
    -0.46
    dafx
    -0.46
    POSITIVE LOGITS
     TextAppearance
    0.65
     reader
    0.64
    MergeFrom
    0.58
    WireFormatLite
    0.58
     READER
    0.57
    orded
    0.55
    __':
    0.55
    results
    0.54
     bare
    0.54
    riction
    0.52
    Act Density 0.001%

    No Known Activations