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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	double
    -0.07
    frequency
    -0.07
    weed
    -0.07
    ุ้
    -0.06
     väl
    -0.06
     overwhelmed
    -0.06
    	wx
    -0.06
    reading
    -0.06
     انرژی
    -0.06
    cil
    -0.06
    POSITIVE LOGITS
     نوف
    0.07
     (:
    0.07
    .getExternal
    0.07
    \Lib
    0.07
     Fuller
    0.07
     Prague
    0.06
    _false
    0.06
    لى
    0.06
     ';↵
    0.06
                               ↵
    0.06
    Act Density 0.145%

    No Known Activations