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

    Neuronpedia

    INDEX
    Explanations

    software tools and development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🖤
    1.05
    constants
    0.98
    👍
    0.93
    یک
    0.92
     ترین
    0.91
    ermek
    0.89
    ych
    0.89
     différen
    0.88
    ៩
    0.88
    جان
    0.87
    POSITIVE LOGITS
     any
    0.77
     sputtering
    0.76
     tinkering
    0.74
     conviv
    0.74
     sneak
    0.73
     Fiji
    0.73
     toss
    0.71
     onto
    0.70
     tat
    0.69
     archery
    0.68
    Act Density 0.001%

    No Known Activations