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

    Neuronpedia

    INDEX
    Explanations

    scientists trust atoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     років
    1.20
     यहीं
    1.13
     stents
    1.08
     YEARS
    1.07
     entendre
    1.04
     years
    1.00
    स्तो
    0.99
    attery
    0.99
     tributaries
    0.98
     decades
    0.96
    POSITIVE LOGITS
     $("
    0.99
     lindos
    0.98
     初期
    0.95
    speople
    0.95
    GIS
    0.94
     सुन्दर
    0.93
     $(".
    0.93
    mps
    0.92
    0.92
     <%=
    0.92
    Act Density 0.001%

    No Known Activations