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

    Neuronpedia

    INDEX
    Explanations

    well-thought-out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سعر
    0.57
     MVC
    0.57
     .
    0.55
     TOC
    0.54
     SLR
    0.54
     Title
    0.52
    ISTS
    0.52
    ERN
    0.52
    ED
    0.51
    ovno
    0.50
    POSITIVE LOGITS
     practising
    0.52
    ]，
    0.50
    訨
    0.50
     beobachten
    0.49
     epidermis
    0.47
    βάλ
    0.46
    嶆
    0.46
     सिंघ
    0.46
    の名
    0.46
    ਟ
    0.45
    Act Density 0.001%

    No Known Activations