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

    Neuronpedia

    INDEX
    Explanations

    request GET username

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dır
    2.31
    ください
    1.75
    eldorf
    1.72
    thema
    1.70
    yong
    1.62
     وعلى
    1.60
     وفي
    1.59
    sy
    1.58
    grund
    1.56
    damn
    1.55
    POSITIVE LOGITS
    או
    1.55
    কা
    1.52
     aches
    1.49
    ュ
    1.46
    ։
    1.46
    િર
    1.43
     effectués
    1.42
    でもある
    1.40
    ما
    1.39
    ванням
    1.39
    Act Density 0.003%

    No Known Activations