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

    Neuronpedia

    INDEX
    Explanations

    impact, morale, or memory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     D
    0.45
    न
    0.43
    s
    0.42
     be
    0.42
    rbind
    0.41
     firmy
    0.41
     return
    0.40
     se
    0.39
    COLOR
    0.39
     sợ
    0.39
    POSITIVE LOGITS
    __);
    0.51
    ವಾರು
    0.51
    的游戏
    0.50
     سلاټونه
    0.50
     პროფილი
    0.50
     〢
    0.50
     розді
    0.50
    のエ
    0.50
     объект
    0.49
    。<
    0.49
    Act Density 0.000%

    No Known Activations