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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ман
    -0.06
     гол
    -0.06
    IGINAL
    -0.06
    ellites
    -0.06
    odore
    -0.06
     contempl
    -0.06
    utsch
    -0.06
    canvas
    -0.06
    zug
    -0.06
     cumpl
    -0.06
    POSITIVE LOGITS
     Crush
    0.07
     tra
    0.07
    처
    0.07
     outra
    0.06
     endings
    0.06
     Spread
    0.06
     Sustainability
    0.06
    一起
    0.06
     {}↵↵
    0.06
     yy
    0.06
    Act Density 0.001%

    No Known Activations