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

    Neuronpedia

    INDEX
    Explanations

    across regions, tasks, or genres

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    px
    0.95
    0.93
    the
    0.91
    est
    0.89
    ef
    0.88
    sk
    0.87
    sv
    0.86
    said
    0.86
    met
    0.85
    sm
    0.84
    POSITIVE LOGITS
     Ál
    1.05
     recentes
    1.03
     instituições
    1.02
     vírus
    1.02
     outils
    0.99
     lancement
    0.99
     rêves
    0.99
     décisions
    0.98
     tué
    0.98
     gás
    0.96
    Act Density 0.001%

    No Known Activations