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

    Neuronpedia

    INDEX
    Explanations

    TYPO

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uniqueness
    -0.06
     testified
    -0.06
     edin
    -0.06
    četně
    -0.06
    Indent
    -0.06
     uzman
    -0.06
     králov
    -0.06
    syn
    -0.06
     jean
    -0.06
     exponential
    -0.06
    POSITIVE LOGITS
    ấy
    0.07
    由
    0.07
    -Co
    0.06
    โล
    0.06
    _PO
    0.06
    (main
    0.06
     MMO
    0.06
    ','".$
    0.06
    ζό
    0.06
    RGBO
    0.06
    Act Density 0.002%

    No Known Activations