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

    Neuronpedia

    INDEX
    Explanations

    just emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     уч
    0.44
     계산
    0.43
     선택
    0.42
     사용할
    0.41
    仿
    0.40
    連接
    0.40
     [&
    0.39
     `<=
    0.39
     постави
    0.38
     CONNECT
    0.38
    POSITIVE LOGITS
     hormone
    0.46
     Hormone
    0.44
    رآ
    0.43
    awaited
    0.42
     Redding
    0.41
     Horm
    0.41
     Lauderdale
    0.40
    loving
    0.40
     hormonal
    0.40
     vesicular
    0.40
    Act Density 0.001%

    No Known Activations