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

    Neuronpedia

    INDEX
    Explanations

    list structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     didn
    0.47
    ↵↵
    0.43
     a
    0.41
     x
    0.39
     high
    0.39
     left
    0.38
     string
    0.38
     some
    0.38
     page
    0.37
     any
    0.37
    POSITIVE LOGITS
    storageModule
    0.37
     yattha
    0.37
    ้วน
    0.35
    Paula
    0.35
    ారీ
    0.35
    шым
    0.34
    Parameterized
    0.34
    SETUP
    0.34
    ΡΑ
    0.34
    Bracketing
    0.34
    Act Density 0.003%

    No Known Activations