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

    Neuronpedia

    INDEX
    Explanations

    found in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    액
    -0.06
     Croat
    -0.06
    mma
    -0.06
    ested
    -0.06
    pur
    -0.06
     Kodi
    -0.06
    ugu
    -0.06
     colonies
    -0.06
     Releases
    -0.06
    50
    -0.06
    POSITIVE LOGITS
    _processed
    0.07
    然而
    0.07
     Desktop
    0.07
    _argument
    0.07
    вет
    0.06
     могу
    0.06
    婷
    0.06
    editable
    0.06
     Trần
    0.06
     UserProfile
    0.06
    Act Density 0.012%

    No Known Activations