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

    Neuronpedia

    INDEX
    Explanations

    spark submit command

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    coats
    1.73
    ェ
    1.71
    ers
    1.70
    ल
    1.69
    ي
    1.68
    त्र
    1.67
    ი
    1.64
     juicy
    1.64
    kere
    1.63
     histoires
    1.59
    POSITIVE LOGITS
    MRI
    1.56
    modifier
    1.56
    鹉
    1.53
    cych
    1.50
    य
    1.45
     siguiente
    1.43
     নিতে
    1.40
    nda
    1.39
     definiert
    1.39
    delegate
    1.38
    Act Density 0.000%

    No Known Activations