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

    Neuronpedia

    INDEX
    Explanations

    drag-and-drop and dragons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    न
    0.90
     diagnóstico
    0.87
    መሳሳይ
    0.86
     bowtie
    0.83
    sessions
    0.83
     avanç
    0.82
    s
    0.81
     পাকিস্তানকে
    0.79
    ávez
    0.79
    ຄວາມ
    0.78
    POSITIVE LOGITS
    flies
    1.40
     dragon
    1.23
     dragons
    1.20
    🐉
    1.11
    拽
    1.07
    🐲
    1.06
    Drag
    1.03
     Drag
    1.01
     Dragon
    1.01
     drag
    1.00
    Act Density 0.045%

    No Known Activations