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

    Neuronpedia

    INDEX
    Explanations

    appending or adding to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    কাব
    0.41
     উচ্চারণ
    0.39
    similarity
    0.38
    dV
    0.38
     Verwendung
    0.38
     interrelated
    0.37
    Similarity
    0.37
     Bezug
    0.37
     উচ্চার
    0.37
    adri
    0.36
    POSITIVE LOGITS
     to
    0.45
    に加え
    0.42
    razine
    0.42
    logne
    0.41
     conquer
    0.39
    ॉल
    0.38
     شہ
    0.37
    ̀n
    0.37
     end
    0.37
     जीतकर
    0.37
    Act Density 0.001%

    No Known Activations