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

    Neuronpedia

    INDEX
    Explanations

    ETH

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zeichnis
    0.44
    centerX
    0.42
     CVD
    0.39
    డీ
    0.39
    နောက်
    0.38
    }}+\
    0.38
    тым
    0.37
    }}\
    0.37
     کدام
    0.37
    তরাং
    0.37
    POSITIVE LOGITS
     تحت
    0.37
     isbn
    0.37
    설
    0.37
     otw
    0.37
     vanwege
    0.37
     proteine
    0.36
    로
    0.36
     inspe
    0.36
     atthe
    0.36
    만
    0.36
    Act Density 0.003%

    No Known Activations