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

    Neuronpedia

    INDEX
    Explanations

    check the box

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ÈRE
    0.62
    amsa
    0.62
     स्वरुप
    0.61
     मुं
    0.60
     Sle
    0.59
     sting
    0.59
     dimensión
    0.59
    λικό
    0.59
     Stre
    0.59
     کړئ
    0.59
    POSITIVE LOGITS
     boxes
    2.01
    boxes
    1.69
     box
    1.65
     Boxes
    1.64
    Boxes
    1.55
     checkboxes
    1.51
    box
    1.50
     बॉक्स
    1.40
     ticks
    1.38
     Box
    1.33
    Act Density 0.014%

    No Known Activations