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

    Neuronpedia

    INDEX
    Explanations

    el

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     کھیلنے
    0.64
    alaman
    0.60
     상세
    0.59
    λαδή
    0.58
     almaya
    0.58
     कुलपति
    0.57
     председа
    0.56
    maal
    0.55
    owników
    0.55
    לות
    0.55
    POSITIVE LOGITS
    ation
    0.74
     Fix
    0.59
    Fix
    0.58
    Wright
    0.58
    ATION
    0.55
     Delight
    0.54
    禛
    0.54
    Sand
    0.54
    Flush
    0.54
    Fl
    0.54
    Act Density 0.001%

    No Known Activations