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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ěn
    -0.06
    [_
    -0.06
    inear
    -0.06
    д
    -0.06
    ditor
    -0.06
    ск
    -0.06
    _cancel
    -0.06
    wendung
    -0.06
    itations
    -0.06
     ▼
    -0.06
    POSITIVE LOGITS
    (jLabel
    0.08
     çalışan
    0.07
    //↵↵↵
    0.06
     Propel
    0.06
     krat
    0.06
     Bison
    0.06
    	↵	↵	↵
    0.06
     월세
    0.06
    COM
    0.06
     Mentor
    0.06
    Act Density 0.193%

    No Known Activations