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

    Neuronpedia

    INDEX
    Explanations

    non-English fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    מוע
    -0.06
    setTimeout
    -0.06
    地下室
    -0.06
    趣
    -0.06
    unky
    -0.06
     clans
    -0.06
    _REV
    -0.06
     stadium
    -0.06
    业界
    -0.06
    แถว
    -0.06
    POSITIVE LOGITS
     EST
    0.08
    Rom
    0.08
     приним
    0.08
    다는
    0.07
     INDEX
    0.07
     manus
    0.07
    Search
    0.07
    jącego
    0.07
    iệm
    0.07
    _fragment
    0.07
    Act Density 0.026%

    No Known Activations