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

    Neuronpedia

    INDEX
    Explanations

    quotes and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ))$
    0.44
    ).^
    0.41
    )=$
    0.41
    )-$
    0.41
    غراف
    0.41
    _'.$
    0.40
    visiae
    0.40
    antiti
    0.40
    =_
    0.40
    -}$
    0.39
    POSITIVE LOGITS
     quote
    0.64
     Quote
    0.60
    quote
    0.54
    Quote
    0.53
     Question
    0.51
     Ten
    0.49
     Quotes
    0.49
     quotation
    0.49
    "...
    0.49
     "[
    0.48
    Act Density 0.000%

    No Known Activations