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

    Neuronpedia

    INDEX
    Explanations

    author and affiliation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     coasters
    0.77
     collectibles
    0.75
     havoc
    0.75
     kittens
    0.75
     heartache
    0.73
     premiums
    0.71
     bracelets
    0.71
     sneakers
    0.71
     carbs
    0.71
     devastation
    0.71
    POSITIVE LOGITS
    University
    0.96
    Universität
    0.85
     University
    0.85
    Université
    0.81
     Université
    0.79
    Institute
    0.77
     Universität
    0.75
    Universidad
    0.73
    Institut
    0.73
    Department
    0.71
    Act Density 0.002%

    No Known Activations