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

    Neuronpedia

    INDEX
    Explanations

    q

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LLC
    -0.07
     Skills
    -0.06
     hunter
    -0.06
    .Itoa
    -0.06
     thoroughly
    -0.06
     offic
    -0.06
     Spa
    -0.06
    _si
    -0.06
    Sys
    -0.06
    Sz
    -0.06
    POSITIVE LOGITS
    ài
    0.07
     nguyện
    0.07
     NGX
    0.06
    wifi
    0.06
    		↵	↵
    0.06
    這
    0.06
     conservation
    0.06
    	↵		↵
    0.06
     exit
    0.06
    .ContentAlignment
    0.06
    Act Density 0.001%

    No Known Activations