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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    植
    -0.07
    ации
    -0.07
    jící
    -0.06
     Lev
    -0.06
     吉
    -0.06
     demi
    -0.06
    (dep
    -0.06
     reprint
    -0.06
     ordinance
    -0.06
    prech
    -0.06
    POSITIVE LOGITS
    _units
    0.07
    .emit
    0.07
     指
    0.07
    .Messaging
    0.06
    ktop
    0.06
     Instructions
    0.06
    .shortcuts
    0.06
    	  ↵
    0.06
     '|'
    0.06
     Lif
    0.06
    Act Density 0.017%

    No Known Activations