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

    Neuronpedia

    INDEX
    Explanations

    OK

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    guide
    -0.07
     probl
    -0.07
    .Spring
    -0.07
    Determin
    -0.06
    еле
    -0.06
    /about
    -0.06
     при
    -0.06
    響
    -0.06
    νος
    -0.06
     Пари
    -0.06
    POSITIVE LOGITS
     handguns
    0.08
     ألف
    0.07
    Go
    0.07
    }↵
    0.06
    )↵↵
    0.06
     so
    0.06
    0.06
    '))↵↵
    0.06
     balcony
    0.06
    ροχή
    0.06
    Act Density 0.012%

    No Known Activations