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

    Neuronpedia

    INDEX
    Explanations

    rows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     STRING
    -0.07
    .hu
    -0.06
    AsString
    -0.06
    	usage
    -0.06
     cleanup
    -0.06
    .part
    -0.06
    "${
    -0.06
     byl
    -0.06
    fluence
    -0.06
     vým
    -0.06
    POSITIVE LOGITS
     tidak
    0.07
     jel
    0.07
    .GetBytes
    0.06
    оличество
    0.06
     rows
    0.06
     fet
    0.06
     Brake
    0.06
     Benjamin
    0.06
    rails
    0.06
    ,)↵
    0.06
    Act Density 0.001%

    No Known Activations