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

    Neuronpedia

    INDEX
    Explanations

    IBM copyright notices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RIP
    -0.08
    omez
    -0.07
    列出
    -0.07
     anche
    -0.07
    triangle
    -0.07
     Pier
    -0.07
     tam
    -0.07
    梯
    -0.07
     itemType
    -0.07
     Cv
    -0.07
    POSITIVE LOGITS
     Essay
    0.08
     descriptive
    0.07
     dejtingsaj
    0.06
    ándose
    0.06
     sæ
    0.06
     USE
    0.06
    verbatim
    0.06
    �
    0.06
    closed
    0.06
     esposa
    0.06
    Act Density 0.023%

    No Known Activations