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

    Neuronpedia

    INDEX
    Explanations

    ; it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     astfel
    0.86
     theres
    0.80
    ebab
    0.77
     pemb
    0.76
     delas
    0.74
     Anyways
    0.74
     anyways
    0.73
     dele
    0.72
     পরিপ্রে
    0.72
     deles
    0.72
    POSITIVE LOGITS
     IT
    0.84
     computer
    0.81
    IT
    0.78
    computer
    0.75
     е
    0.73
     Computer
    0.72
    Computer
    0.72
    أ
    0.71
     computers
    0.70
    computers
    0.68
    Act Density 0.325%

    No Known Activations