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

    Neuronpedia

    INDEX
    Explanations

    Just/how followed by topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esche
    0.56
     tantal
    0.54
     neden
    0.52
     debunk
    0.52
     ooz
    0.51
     senza
    0.50
     improvis
    0.50
     exasper
    0.49
     genuinely
    0.49
     trying
    0.49
    POSITIVE LOGITS
    Months
    0.62
    Currency
    0.58
    Month
    0.53
    Population
    0.53
    Category
    0.52
    History
    0.52
    Economy
    0.52
    Delivery
    0.51
    Translator
    0.50
     UNITS
    0.50
    Act Density 0.000%

    No Known Activations