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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    子の
    -0.07
     olumsuz
    -0.07
    ンの
    -0.07
    开展
    -0.07
    ULD
    -0.07
     таком
    -0.07
    ificacion
    -0.07
    -trained
    -0.06
    ланд
    -0.06
     تبلی
    -0.06
    POSITIVE LOGITS
    ENOMEM
    0.07
     hoses
    0.07
    ]'↵
    0.07
     mayoría
    0.06
     continents
    0.06
    $↵
    0.06
    },
↵
    0.06
     convoy
    0.06
     Herman
    0.06
    }',↵
    0.06
    Act Density 0.000%

    No Known Activations