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

    Neuronpedia

    INDEX
    Explanations

    Fast

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cynthia
    -0.07
     Lamar
    -0.07
    -0.07
     Sylv
    -0.07
     Rack
    -0.07
     tamamen
    -0.07
     Cot
    -0.07
     sufficient
    -0.07
     Laf
    -0.06
     Wouldn
    -0.06
    POSITIVE LOGITS
    ">'.
    0.06
     Про
    0.06
    ++];↵
    0.06
     systém
    0.06
    '))
↵
    0.06
     ποι
    0.06
    -push
    0.06
    nh
    0.06
     strm
    0.06
    ointed
    0.06
    Act Density 0.010%

    No Known Activations