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

    Neuronpedia

    INDEX
    Explanations

    full

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     advantageous
    -0.08
     protective
    -0.08
    üng
    -0.08
     eenvoudige
    -0.07
     IOC
    -0.07
    anfaat
    -0.07
    Bits
    -0.07
    IMA
    -0.07
     favorable
    -0.07
    -headed
    -0.07
    POSITIVE LOGITS
     entière
    0.11
     كاملة
    0.10
     :(↵↵
    0.10
     complète
    0.10
     полноцен
    0.10
     truly
    0.09
     completas
    0.08
     полностью
    0.08
     unquestionably
    0.08
     పూర్తి
    0.08
    Act Density 0.019%

    No Known Activations