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

    Neuronpedia

    INDEX
    Explanations

    legal context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expectations
    -0.07
     повіт
    -0.06
     быстро
    -0.06
    елич
    -0.06
    学习
    -0.06
    ніч
    -0.06
    .rule
    -0.06
    .qu
    -0.06
    adam
    -0.06
    ('\\
    -0.06
    POSITIVE LOGITS
    Weight
    0.06
     teh
    0.06
     Weight
    0.06
     TN
    0.06
     curated
    0.06
    Liver
    0.06
     जर
    0.06
    chor
    0.06
     felt
    0.06
     ));↵
    0.06
    Act Density 0.005%

    No Known Activations