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

    Neuronpedia

    INDEX
    Explanations

    Code and versions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    θούν
    -0.07
    もう
    -0.07
    iscopal
    -0.06
     dés
    -0.06
    idental
    -0.06
    	method
    -0.06
     дит
    -0.06
    '];?>
    -0.06
     betrayed
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Algorithms
    0.07
     borders
    0.06
    держ
    0.06
    Κ
    0.06
    -history
    0.06
     sdk
    0.06
     Internal
    0.06
    flag
    0.06
     ك
    0.06
     --↵
    0.06
    Act Density 0.019%

    No Known Activations