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

    Neuronpedia

    INDEX
    Explanations

    asking for specific details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hence
    0.94
     Hence
    0.93
     çoğu
    0.92
     нередко
    0.88
     Often
    0.88
     Поэтому
    0.87
    Hence
    0.87
    ሃ
    0.87
     Затем
    0.86
    өп
    0.84
    POSITIVE LOGITS
     particular
    2.00
     specific
    1.99
    特定の
    1.61
    某个
    1.60
     specifico
    1.59
    specific
    1.53
     конкре
    1.52
     특정
    1.47
     eller
    1.46
    或者是
    1.46
    Act Density 1.279%

    No Known Activations