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

    Neuronpedia

    INDEX
    Explanations

    internet text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Getting
    -0.07
     pain
    -0.07
     andere
    -0.07
    328
    -0.06
    _string
    -0.06
     epidemic
    -0.06
    .reader
    -0.06
    oly
    -0.06
     growth
    -0.06
     hunter
    -0.06
    POSITIVE LOGITS
    ισ
    0.07
     @[
    0.06
     부탁
    0.06
     ✔
    0.06
     Osama
    0.06
     credible
    0.06
    ]';↵
    0.06
    LETE
    0.06
     네이트온
    0.06
    details
    0.06
    Act Density 0.244%

    No Known Activations