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

    Neuronpedia

    INDEX
    Explanations

    asking for details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tehd
    0.60
    ята
    0.57
     theor
    0.56
     ter
    0.56
     viable
    0.54
    !</
    0.54
    !<
    0.54
     theory
    0.53
     justifies
    0.53
    éd
    0.53
    POSITIVE LOGITS
    回答
    0.79
     enquire
    0.77
     Información
    0.75
    確認
    0.75
     سوال
    0.73
    PersonalInfo
    0.72
     please
    0.71
    নিম্ন
    0.69
     참석
    0.69
    निम्नलिखित
    0.69
    Act Density 0.044%

    No Known Activations