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

    Neuronpedia

    INDEX
    Explanations

    yes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unordered
    -0.07
    聞
    -0.06
    ενο
    -0.06
    论文
    -0.06
     wishlist
    -0.06
     оз
    -0.06
    _de
    -0.06
    Dims
    -0.06
    _periods
    -0.06
     позд
    -0.06
    POSITIVE LOGITS
     yes
    0.08
     homeland
    0.07
    326
    0.06
    156
    0.06
    .addAction
    0.06
     beef
    0.06
     yeah
    0.06
     Yes
    0.06
    ser
    0.06
     hashes
    0.06
    Act Density 0.013%

    No Known Activations