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

    Neuronpedia

    INDEX
    Explanations

    emojis or abbreviations for technologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Priorities
    0.61
     заме
    0.60
     ranged
    0.57
     traveller
    0.56
     hailed
    0.56
    &#
    0.55
    ​
    0.55
     horizon
    0.54
     চাল
    0.54
     crashes
    0.54
    POSITIVE LOGITS
    czenie
    0.75
     Arzneim
    0.74
    cose
    0.74
     połą
    0.71
     gesund
    0.70
    cA
    0.70
     آزمایش
    0.69
     بیمار
    0.68
     розу
    0.68
    علوم
    0.67
    Act Density 0.001%

    No Known Activations