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

    Neuronpedia

    INDEX
    Explanations

    EOF delimiter, HTML, HEAD

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ও
    2.02
    ে
    1.96
     чтобы
    1.78
    वर
    1.73
    iem
    1.71
    ும்போது
    1.70
    েও
    1.69
    ي
    1.68
    не
    1.66
    ં
    1.61
    POSITIVE LOGITS
    Smoothing
    1.58
    Manager
    1.57
    та
    1.55
    Pipe
    1.54
    亠
    1.53
     overlying
    1.49
    கம்
    1.48
    Maven
    1.48
    ிகளின்
    1.48
     인
    1.47
    Act Density 0.000%

    No Known Activations