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

    Neuronpedia

    INDEX
    Explanations

    match or matching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ب
    1.50
    ال
    1.29
    торой
    1.28
    ATORS
    1.27
    ление
    1.25
    ruta
    1.25
     taxonomy
    1.25
    د
    1.23
    loud
    1.20
    ご
    1.20
    POSITIVE LOGITS
     wits
    1.58
     Selon
    1.42
    你
    1.41
    ͯ
    1.39
     gusto
    1.35
     gosh
    1.32
    넉
    1.32
    ⃛
    1.30
    gladbach
    1.29
     digraph
    1.24
    Act Density 0.038%

    No Known Activations