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

    Neuronpedia

    INDEX
    Explanations

    specific sequences or identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    んにちは
    0.93
    гато
    0.88
     erythe
    0.84
     cryptocur
    0.82
    ንዱ
    0.80
    )`,
    0.80
    kag
    0.79
    StructOf
    0.79
    蒉
    0.78
    arrayList
    0.77
    POSITIVE LOGITS
    ى
    1.17
    .
    1.05
    কে
    1.05
    1
    1.02
    ?
    1.02
    ного
    0.99
    اته
    0.97
    6
    0.97
    ’
    0.97
    
    0.96
    Act Density 0.062%

    No Known Activations