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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amination
    -0.07
    ordering
    -0.07
     anchor
    -0.06
     beings
    -0.06
    iversary
    -0.06
     Origins
    -0.06
     Draw
    -0.06
     Robots
    -0.06
     mansion
    -0.06
    ニニ
    -0.06
    POSITIVE LOGITS
    _gallery
    0.07
     of
    0.06
    なくな
    0.06
     unten
    0.06
     Athena
    0.06
    nesia
    0.06
    .shortcuts
    0.06
    átní
    0.06
                
↵
    0.06
    ÜR
    0.06
    Act Density 0.005%

    No Known Activations