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

    Neuronpedia

    INDEX
    Explanations

    dolphins hunt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    σι
    0.41
    oirs
    0.40
     والمع
    0.39
    تس
    0.39
     purified
    0.39
    สง
    0.38
     đẩy
    0.38
    ễm
    0.38
    δας
    0.37
    HAEL
    0.37
    POSITIVE LOGITS
     premier
    0.49
    i
    0.44
    premier
    0.42
     divide
    0.42
     spoken
    0.41
     ilg
    0.40
     ug
    0.40
    nextLine
    0.39
     कड़ी
    0.39
     সফদর
    0.39
    Act Density 0.000%

    No Known Activations