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

    Neuronpedia

    INDEX
    Explanations

    Code and documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CDF
    -0.08
    47
    -0.07
    Ale
    -0.07
    923
    -0.06
    fold
    -0.06
     сентября
    -0.06
    610
    -0.06
     году
    -0.06
    ків
    -0.06
    523
    -0.06
    POSITIVE LOGITS
    ριστ
    0.07
     superb
    0.07
    (itemView
    0.07
    .Export
    0.07
    _artist
    0.06
    �
    0.06
     ventured
    0.06
     Choosing
    0.06
     excer
    0.06
    INARY
    0.06
    Act Density 0.060%

    No Known Activations