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

    Neuronpedia

    INDEX
    Explanations

    advice followed by enumeration or end-markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jenis
    0.61
    아
    0.60
    Beth
    0.59
     Jenis
    0.58
     przewod
    0.57
    ಂ
    0.56
    Рус
    0.55
     राघव
    0.55
    টে
    0.55
    훔
    0.54
    POSITIVE LOGITS
    ẩu
    0.64
     etc
    0.62
    亦
    0.62
     Etc
    0.61
     тощо
    0.61
     Lastly
    0.58
    ']))
    0.57
    stige
    0.57
     வீட்டு
    0.56
     इत्यादि
    0.56
    Act Density 0.029%

    No Known Activations