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

    Neuronpedia

    INDEX
    Explanations

    period token

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    各种
    -0.07
    `='$
    -0.07
    ��
    -0.06
    solver
    -0.06
     YE
    -0.06
    .responses
    -0.06
    -ever
    -0.06
    inactive
    -0.06
     сайті
    -0.06
     σύ
    -0.06
    POSITIVE LOGITS
     nullptr
    0.07
     FLAC
    0.06
    receive
    0.06
    Entropy
    0.06
    afia
    0.06
     Lotus
    0.06
    .Keyword
    0.06
     restores
    0.06
     Leakage
    0.06
     Orn
    0.06
    Act Density 0.860%

    No Known Activations