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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plac
    -0.07
    �
    -0.07
    Txt
    -0.07
    文
    -0.06
    ugador
    -0.06
    кар
    -0.06
    ικές
    -0.06
    _interrupt
    -0.06
    Watching
    -0.06
    _pod
    -0.06
    POSITIVE LOGITS
     дво
    0.07
    holds
    0.07
    ».↵↵
    0.06
    olor
    0.06
     essere
    0.06
     covenant
    0.06
    nelle
    0.06
     stddev
    0.06
     renamed
    0.06
    чий
    0.06
    Act Density 0.114%

    No Known Activations