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

    Neuronpedia

    INDEX
    Explanations

    were these

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     KL
    -0.07
    BinContent
    -0.07
    CL
    -0.06
    _instance
    -0.06
     DriverManager
    -0.06
     بار
    -0.06
    AllowAnonymous
    -0.06
     Sampler
    -0.06
    只是
    -0.06
     národ
    -0.06
    POSITIVE LOGITS
    These
    0.10
     these
    0.09
    “These
    0.09
     These
    0.09
    these
    0.09
    credit
    0.07
    "These
    0.07
     تكييف
    0.07
     nowadays
    0.06
    dictions
    0.06
    Act Density 0.080%

    No Known Activations