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

    Neuronpedia

    INDEX
    Explanations

    Universities and Departments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Harvard
    0.54
    Harvard
    0.54
     Stanford
    0.51
    Stanford
    0.51
     Boston
    0.47
     Yale
    0.44
     Silicon
    0.42
    Boston
    0.42
     Princeton
    0.41
     McKinsey
    0.41
    POSITIVE LOGITS
     Departamento
    0.57
    Department
    0.56
     Badajoz
    0.54
     Department
    0.54
    Departamento
    0.52
     Orissa
    0.51
     Rajasthan
    0.50
     Manipur
    0.49
    Rajasthan
    0.49
     Département
    0.48
    Act Density 0.001%

    No Known Activations