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

    Neuronpedia

    INDEX
    Explanations

    new concepts or situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    比較的
    0.38
    НО
    0.36
    ឃ
    0.36
    тится
    0.35
    抟
    0.34
    CER
    0.34
    various
    0.34
    НУ
    0.34
    decreasing
    0.33
    க்கமாக
    0.33
    POSITIVE LOGITS
     new
    3.97
     nieuwe
    3.47
     নতুন
    3.45
     새로운
    3.42
     nuovi
    3.41
     nuevos
    3.39
     новых
    3.39
     neuen
    3.38
     nuove
    3.36
    新的
    3.34
    Act Density 0.091%

    No Known Activations