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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    引用频次
    -0.06
     purified
    -0.06
     density
    -0.06
     gut
    -0.06
    逆
    -0.06
     galaxies
    -0.06
            
↵
↵
    -0.06
     tố
    -0.06
    -development
    -0.06
    privation
    -0.06
    POSITIVE LOGITS
     principalColumn
    0.07
    Strange
    0.06
    ');"
    0.06
     عو
    0.06
    _unicode
    0.06
    .tiles
    0.06
     Phi
    0.06
    mile
    0.06
     spotify
    0.06
     Freed
    0.06
    Act Density 0.033%

    No Known Activations