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

    Neuronpedia

    INDEX
    Explanations

    gold and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ethics
    0.80
     earthy
    0.74
     Operation
    0.73
     Gew
    0.72
     Operations
    0.71
     Terrain
    0.71
     Religious
    0.71
     ribs
    0.69
     Functions
    0.69
     spoiler
    0.69
    POSITIVE LOGITS
    ığımızda
    1.07
    新
    0.95
     нового
    0.93
     جديدة
    0.92
    如果
    0.92
     naš
    0.88
    م
    0.87
    SelectList
    0.86
    minutes
    0.86
    ందరు
    0.86
    Act Density 0.001%

    No Known Activations