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

    Neuronpedia

    INDEX
    Explanations

    however, updates, while

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vuol
    0.55
     খাদ্য
    0.49
     ему
    0.48
     الفرنسي
    0.48
     aper
    0.47
     adulte
    0.47
     acquistare
    0.46
     genel
    0.45
     hrane
    0.45
     pavimento
    0.45
    POSITIVE LOGITS
    ിട
    0.48
    Comedy
    0.46
    。
    0.45
    Emily
    0.45
    rés
    0.43
    érico
    0.42
    *
    0.42
    I
    0.41
    ا۔
    0.40
    Tony
    0.40
    Act Density 0.001%

    No Known Activations