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

    Neuronpedia

    INDEX
    Explanations

    "The" followed by specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Its
    0.97
     Its
    0.93
    the
    0.87
    라는
    0.85
    :
    0.82
     dessen
    0.81
    |
    0.80
    what
    0.79
    its
    0.79
     its
    0.78
    POSITIVE LOGITS
     interplay
    1.12
    oretically
    1.11
     lack
    1.03
     applicability
    1.02
     mechanisms
    0.97
    ophylline
    0.95
     distinction
    0.93
     discrepancy
    0.93
     genomes
    0.91
     prevalence
    0.90
    Act Density 0.113%

    No Known Activations