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

    Neuronpedia

    INDEX
    Explanations

    punctuation/conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uate
    -0.07
    (pages
    -0.07
     боль
    -0.07
    왔
    -0.06
    pointer
    -0.06
    ----↵↵
    -0.06
    StringBuilder
    -0.06
    亭
    -0.06
    ニア
    -0.06
    _output
    -0.06
    POSITIVE LOGITS
     Electron
    0.07
     eski
    0.06
    028
    0.06
    coil
    0.06
     workload
    0.06
    يمكن
    0.06
     arms
    0.06
    heten
    0.06
    pellier
    0.06
     Jerseys
    0.06
    Act Density 0.058%

    No Known Activations