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

    Neuronpedia

    INDEX
    Explanations

    come in many forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Seminar
    0.45
    ')
    0.41
     Pricing
    0.38
     available
    0.37
     process
    0.36
     surfaces
    0.36
     procedure
    0.36
     Register
    0.36
     markets
    0.35
     depths
    0.35
    POSITIVE LOGITS
    Attached
    0.51
     baggage
    0.50
    ╥
    0.45
     ответственность
    0.45
     hinzu
    0.44
     Attached
    0.44
    叁
    0.43
    责任
    0.43
     tanggung
    0.42
     पैकेज
    0.42
    Act Density 0.011%

    No Known Activations