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

    Neuronpedia

    INDEX
    Explanations

    article numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aimanapun
    0.35
     ሥ
    0.34
    tywn
    0.34
    POSTFIELDS
    0.34
    ｛
    0.33
    ியது
    0.33
     ܥ
    0.33
    ৫৫
    0.33
    御
    0.33
    有什么
    0.33
    POSITIVE LOGITS
    actions
    0.38
    disc
    0.38
     atos
    0.37
     값이
    0.36
     seventeenth
    0.35
    茨
    0.34
     smooth
    0.34
    cussions
    0.34
     વરસ
    0.34
    महा
    0.33
    Act Density 0.003%

    No Known Activations