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

    Neuronpedia

    INDEX
    Explanations

    Library

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Devils
    -0.07
    (err
    -0.07
    Position
    -0.06
    ,_
    -0.06
     над
    -0.06
    .Template
    -0.06
     volont
    -0.06
     ++;↵
    -0.06
     Rotterdam
    -0.06
     Mand
    -0.06
    POSITIVE LOGITS
     Library
    0.19
    Library
    0.19
    -library
    0.11
    .library
    0.11
    ibrary
    0.10
    RARY
    0.09
    _library
    0.08
    _LIBRARY
    0.08
    library
    0.08
     boto
    0.07
    Act Density 0.005%

    No Known Activations