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

    Neuronpedia

    INDEX
    Explanations

    programming languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Monkey
    -0.07
    Rod
    -0.06
     eing
    -0.06
    _ak
    -0.06
     Raised
    -0.06
     Nep
    -0.06
     Irene
    -0.06
     Gong
    -0.06
     Island
    -0.06
    onu
    -0.06
    POSITIVE LOGITS
    graduate
    0.07
     кіль
    0.07
     Володими
    0.07
     kicks
    0.07
     â
    0.07
     Bengal
    0.07
    requ
    0.07
    健康
    0.07
    LOOK
    0.07
     mastering
    0.06
    Act Density 0.057%

    No Known Activations