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

    Neuronpedia

    INDEX
    Explanations

    Cabinets and closets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Schultz
    -0.07
     Torch
    -0.07
     kẻ
    -0.07
    WRAPPER
    -0.07
    城市
    -0.06
    inize
    -0.06
    ама
    -0.06
    .ini
    -0.06
    -basket
    -0.06
     Rebellion
    -0.06
    POSITIVE LOGITS
    ày
    0.07
    mos
    0.06
    ีว
    0.06
    _coin
    0.06
    Proj
    0.06
    毎
    0.06
     associ
    0.06
     intersect
    0.06
    股份
    0.06
     lightweight
    0.06
    Act Density 0.049%

    No Known Activations