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

    Neuronpedia

    INDEX
    Explanations

    specially programmed or designed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    1.39
    </em>
    1.20
    the
    1.17
     the
    1.01
    am
    0.96
     sozial
    0.94
    ні
    0.92
     gateway
    0.92
    </h3>
    0.91
     place
    0.90
    POSITIVE LOGITS
    يل
    0.98
    jší
    0.92
     Increases
    0.88
    ifier
    0.83
     postérieurs
    0.83
     Medications
    0.81
    nger
    0.80
    ක්
    0.80
     specially
    0.79
    lier
    0.79
    Act Density 0.001%

    No Known Activations