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

    Neuronpedia

    INDEX
    Explanations

    culmination of tensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ingresso
    0.57
    ческого
    0.55
    נה
    0.50
    뿍
    0.49
    נים
    0.49
    tahun
    0.49
     alimento
    0.48
    ране
    0.48
    0.47
    लॉक
    0.46
    POSITIVE LOGITS
    op
    0.43
    分
    0.42
     MPL
    0.40
    ByteArray
    0.40
     গু
    0.39
    C
    0.39
     Comm
    0.38
    Warren
    0.38
    尔多
    0.38
     OA
    0.38
    Act Density 0.003%

    No Known Activations