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

    Neuronpedia

    INDEX
    Explanations

    special characters and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     questions
    0.43
    *
    0.40
    Clear
    0.40
    Cm
    0.40
    ском
    0.38
    Questions
    0.38
     السؤال
    0.38
    Nest
    0.38
    myItemType
    0.38
    cm
    0.37
    POSITIVE LOGITS
     Medic
    0.44
     Appropri
    0.41
     दै
    0.39
     "`
    0.38
     Dat
    0.38
     hyp
    0.38
     judi
    0.37
     ബന്ധ
    0.37
     അതി
    0.37
     Garza
    0.37
    Act Density 0.002%

    No Known Activations