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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (info
    -0.07
    .Highlight
    -0.07
    _yaml
    -0.06
    	x
    -0.06
    :{↵
    -0.06
     웹
    -0.06
     lizard
    -0.06
    ظام
    -0.06
     frames
    -0.06
    .Batch
    -0.06
    POSITIVE LOGITS
    СР
    0.06
     endTime
    0.06
     системи
    0.06
    Montserrat
    0.06
     sentir
    0.06
     cultivation
    0.06
     COP
    0.06
     Kỳ
    0.06
    提
    0.06
    тож
    0.06
    Act Density 0.189%

    No Known Activations