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

    Neuronpedia

    INDEX
    Explanations

    "; followed by //

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Universit
    0.44
     Diesel
    0.41
     ឬ
    0.41
     Recherches
    0.40
     leaner
    0.40
     userCollection
    0.40
     feeds
    0.39
     feed
    0.39
     au
    0.39
     learnt
    0.39
    POSITIVE LOGITS
    зу
    0.42
    ці
    0.41
    ❾
    0.40
    cei
    0.39
    HRIM
    0.39
    normalize
    0.39
    Multiply
    0.39
     শিশু
    0.39
     মেজর
    0.39
    ופ
    0.38
    Act Density 0.000%

    No Known Activations