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

    Neuronpedia

    INDEX
    Explanations

    travel, locations, operating systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yarns
    0.51
     thorns
    0.46
     splashes
    0.45
     tarsi
    0.45
     spores
    0.44
     apparition
    0.44
     materiales
    0.44
     misfit
    0.44
     esclus
    0.44
     fungi
    0.43
    POSITIVE LOGITS
     University
    0.57
    University
    0.49
     California
    0.49
     Boston
    0.46
     Cambridge
    0.46
     Edison
    0.44
     Massachusetts
    0.44
    高考
    0.43
     Miami
    0.43
     Chicago
    0.42
    Act Density 0.000%

    No Known Activations