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

    Neuronpedia

    INDEX
    Explanations

    email salutations with placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    op
    0.28
    ф
    0.26
    ($
    0.26
    ｐ
    0.26
    Amar
    0.26
    いろんな
    0.26
    aspetto
    0.26
    OP
    0.25
     (@
    0.25
    ہرے
    0.25
    POSITIVE LOGITS
    醎
    0.30
     ______
    0.29
     persuasive
    0.29
     ____
    0.29
    ____
    0.29
     ________
    0.29
     BSTC
    0.28
    んにちは
    0.28
     منصوب
    0.28
    thorne
    0.28
    Act Density 0.137%

    No Known Activations