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

    Neuronpedia

    INDEX
    Explanations

    please reach for help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    對於
    0.52
    对于
    0.48
    關於
    0.47
     when
    0.46
    关于
    0.45
     जेव्हा
    0.45
     about
    0.43
     για
    0.42
     về
    0.41
    ப்பதால்
    0.41
    POSITIVE LOGITS
     aşağıdaki
    0.54
     volgende
    0.53
     निम्नलिखित
    0.52
     다음과
    0.51
     Voici
    0.50
     Majid
    0.49
     berikut
    0.48
     folgenden
    0.48
     Atau
    0.48
     seguintes
    0.48
    Act Density 0.224%

    No Known Activations