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

    Neuronpedia

    INDEX
    Explanations

    specific contextsornear the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ijom
    0.48
     специалист
    0.46
    ᄋ
    0.44
    hotels
    0.42
    hops
    0.42
    েলের
    0.42
     სპეცი
    0.42
    ពិសេស
    0.42
    ights
    0.41
    avas
    0.41
    POSITIVE LOGITS
    面の
    0.44
     اینکه
    0.41
     dessert
    0.40
     Chew
    0.40
    捻
    0.40
     axe
    0.39
     Oliva
    0.39
     Perrin
    0.39
     Kitten
    0.39
    آور
    0.38
    Act Density 36.353%

    No Known Activations