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

    Neuronpedia

    INDEX
    Explanations

    higher end, closer, quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    バター
    0.50
    বু
    0.39
     <
    0.38
    cur
    0.36
    ಲೇ
    0.35
    baik
    0.35
    ดี
    0.35
    워
    0.35
     হি
    0.34
    emb
    0.34
    POSITIVE LOGITS
     whereas
    0.48
     最後
    0.43
     iesp
    0.42
     sedangkan
    0.41
    Maxim
    0.40
    Whereas
    0.39
     Whereas
    0.38
    に近い
    0.38
    姗
    0.38
     വരെ
    0.37
    Act Density 0.012%

    No Known Activations