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

    Neuronpedia

    INDEX
    Explanations

    76

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ortadan
    -0.07
     straw
    -0.07
     aan
    -0.07
    -archive
    -0.06
     fraud
    -0.06
    شتر
    -0.06
    �
    -0.06
    nob
    -0.06
    ＼↵
    -0.06
    isible
    -0.06
    POSITIVE LOGITS
     dram
    0.07
    .IsAny
    0.07
     QVector
    0.07
    とな
    0.06
    	suite
    0.06
    make
    0.06
    reating
    0.06
    んで
    0.06
    /free
    0.06
    skill
    0.06
    Act Density 0.004%

    No Known Activations