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

    Neuronpedia

    INDEX
    Explanations

    universities and colleges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     UCLA
    0.60
    Stanford
    0.60
    stanford
    0.60
     Stanford
    0.58
     Harvard
    0.53
     Yale
    0.52
    Harvard
    0.50
    Yale
    0.46
    berkeley
    0.46
    taobao
    0.45
    POSITIVE LOGITS
     Liberal
    0.60
     Dominican
    0.59
     liberal
    0.55
     Biology
    0.55
     Franciscan
    0.54
    Liberal
    0.54
    ONU
    0.54
     Lutheran
    0.52
     ONU
    0.52
    Biology
    0.50
    Act Density 0.003%

    No Known Activations