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

    Neuronpedia

    INDEX
    Explanations

    Mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Element
    -0.07
     Cage
    -0.06
     Gods
    -0.06
     cm
    -0.06
     Investing
    -0.06
     sürekli
    -0.06
     assigned
    -0.06
     зал
    -0.06
    orris
    -0.06
    桌
    -0.06
    POSITIVE LOGITS
    ến
    0.06
    >'
    0.06
    /math
    0.06
     sickness
    0.06
    .var
    0.06
     موسی
    0.06
     quanto
    0.06
    _MISS
    0.06
    ↵↵↵↵↵↵↵↵↵
    0.06
    аб
    0.06
    Act Density 0.019%

    No Known Activations