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

    Neuronpedia

    INDEX
    Explanations

    fundamental piece of technology/property

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Robust
    0.41
     dalej
    0.41
     Robust
    0.38
     bf
    0.37
    濫
    0.37
    лишком
    0.36
     সাহস
    0.36
    ുകെ
    0.36
    꿋
    0.35
     এক্ষেত্রে
    0.35
    POSITIVE LOGITS
    ít
    0.42
    ost
    0.41
    нд
    0.39
    тацию
    0.37
    ised
    0.37
     Bengal
    0.37
    iconfont
    0.37
    werking
    0.36
    yz
    0.36
     distortion
    0.36
    Act Density 0.000%

    No Known Activations