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

    Neuronpedia

    INDEX
    Explanations

    the end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вен
    0.65
    จทย์
    0.65
     happiness
    0.63
    romatic
    0.62
    สั่ง
    0.62
     للأ
    0.60
     cried
    0.59
     husk
    0.59
    чь
    0.59
    雀
    0.59
    POSITIVE LOGITS
     end
    3.49
    end
    2.74
     End
    2.73
    End
    2.64
     END
    2.42
     beginning
    2.30
    END
    2.27
     конец
    2.26
     конца
    2.17
    beginning
    2.14
    Act Density 0.133%

    No Known Activations