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

    Neuronpedia

    INDEX
    Explanations

    anticipation of desires

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ওপর
    0.39
    同时
    0.38
     বিকল্প
    0.37
     тебе
    0.36
     μπ
    0.36
     {
    0.36
     も
    0.35
     warning
    0.35
     υπό
    0.35
    origines
    0.35
    POSITIVE LOGITS
     eenvoud
    0.48
     anticipates
    0.46
     childrens
    0.46
     simples
    0.43
     personal
    0.41
     desires
    0.41
     prévoit
    0.40
     wanting
    0.40
     childish
    0.40
     البحث
    0.40
    Act Density 0.003%

    No Known Activations