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

    Neuronpedia

    INDEX
    Explanations

    end of code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     должности
    0.38
    Укупно
    0.37
     Holly
    0.37
     coasters
    0.37
    ➼
    0.37
    }_{+}^{
    0.36
     घास
    0.36
    ))>
    0.36
    वरिश
    0.36
    趙
    0.36
    POSITIVE LOGITS
     End
    0.79
    End
    0.76
     end
    0.76
    end
    0.74
     ending
    0.66
     نهاية
    0.61
     پایان
    0.60
    END
    0.60
     END
    0.59
    glEnd
    0.56
    Act Density 0.008%

    No Known Activations