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

    Neuronpedia

    INDEX
    Explanations

    followed by Lateral

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    зить
    0.70
     имеют
    0.69
    ো
    0.68
     найти
    0.66
     আহত
    0.64
     zbyt
    0.64
    ต่างๆ
    0.63
     বহু
    0.62
    гел
    0.61
    ্স
    0.60
    POSITIVE LOGITS
    mén
    0.92
    㽞
    0.86
    <0xB2>
    0.86
    푸
    0.83
    saraba
    0.81
    nului
    0.80
     semakin
    0.79
    釷
    0.78
    㕣
    0.78
    㴓
    0.78
    Act Density 0.003%

    No Known Activations