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

    Neuronpedia

    INDEX
    Explanations

    average heights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "].
    0.38
    以
    0.37
     Nxb
    0.37
    >.
    0.36
    하기
    0.36
    这么多
    0.36
    一年
    0.34
    一个
    0.34
    "><
    0.34
     применять
    0.34
    POSITIVE LOGITS
     own
    0.41
     throat
    0.41
     próprios
    0.41
     livelihood
    0.38
     shoes
    0.38
    ந்த
    0.37
    สะ
    0.37
     lungs
    0.37
     собственные
    0.37
     socks
    0.36
    Act Density 0.000%

    No Known Activations