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

    Neuronpedia

    INDEX
    Explanations

    Creating explanations or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    노
    0.43
    겁
    0.42
     olvid
    0.42
    lname
    0.41
    보다
    0.41
    Ђ
    0.40
     یاد
    0.40
     terbesar
    0.40
    Concini
    0.40
    ल्फी
    0.39
    POSITIVE LOGITS
     reef
    0.46
    芾
    0.45
    衩
    0.44
     ওকে
    0.44
     গোলাপ
    0.43
     veget
    0.43
     java
    0.42
     проник
    0.42
    郃
    0.42
    ಾದರೆ
    0.42
    Act Density 0.000%

    No Known Activations