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

    Neuronpedia

    INDEX
    Explanations

    relative pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ups
    -0.08
     jackets
    -0.07
    Reflection
    -0.07
    .IsSuccess
    -0.07
     kullanı
    -0.07
    ミ
    -0.06
    传奇
    -0.06
    orative
    -0.06
    .ui
    -0.06
    ela
    -0.06
    POSITIVE LOGITS
    538
    0.06
     AUDIO
    0.06
     Obj
    0.06
    (price
    0.06
     кос
    0.06
     Episodes
    0.06
    _CONST
    0.06
     admins
    0.06
     Carlo
    0.06
     ￥
    0.06
    Act Density 0.080%

    No Known Activations