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

    Neuronpedia

    INDEX
    Explanations

    code and legal text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reward
    -0.06
     Dak
    -0.06
    (sock
    -0.06
     prostituerade
    -0.06
     gang
    -0.06
    .Description
    -0.06
     zelf
    -0.06
     장
    -0.06
    _site
    -0.06
    _arrays
    -0.06
    POSITIVE LOGITS
    ینی
    0.07
    27
    0.07
    orem
    0.06
    anian
    0.06
    Expert
    0.06
     nth
    0.06
    ???
    0.06
    Below
    0.06
     و
    0.06
    ética
    0.06
    Act Density 0.000%

    No Known Activations