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

    Neuronpedia

    INDEX
    Explanations

    reinforcement learning, AI topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    812
    -0.07
     script
    -0.07
    uzzle
    -0.07
    Language
    -0.07
    .adj
    -0.06
     secure
    -0.06
    redit
    -0.06
    ENTA
    -0.06
    ewriter
    -0.06
     python
    -0.06
    POSITIVE LOGITS
     Miche
    0.06
     peppers
    0.06
    のお
    0.06
    、な
    0.06
     nudity
    0.06
     Rooney
    0.06
     Dave
    0.06
     plunge
    0.06
    ุงเทพมหานคร
    0.06
    (cps
    0.06
    Act Density 0.012%

    No Known Activations