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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ступ
    -0.06
    ë
    -0.06
     thép
    -0.06
    France
    -0.06
     주
    -0.06
     PM
    -0.06
    NH
    -0.06
    appro
    -0.06
     всю
    -0.06
    apps
    -0.06
    POSITIVE LOGITS
    期
    0.07
     어머니
    0.06
    userRepository
    0.06
     Jewelry
    0.06
     buffered
    0.06
    TextLabel
    0.06
     submits
    0.06
    (for
    0.06
    'util
    0.06
    (text
    0.06
    Act Density 0.005%

    No Known Activations