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

    Neuronpedia

    INDEX
    Explanations

    select records and facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     innebär
    0.42
     acredito
    0.40
    ledes
    0.39
     acredita
    0.38
    আগ
    0.37
    NameValuePair
    0.36
     identifies
    0.36
    発表
    0.36
     означает
    0.36
     এসেছি
    0.36
    POSITIVE LOGITS
    数值
    0.49
    总
    0.46
    蓝
    0.45
    时的
    0.45
     שהוא
    0.44
    减
    0.44
    自动
    0.44
    精确
    0.44
    作为
    0.43
    总体
    0.43
    Act Density 0.007%

    No Known Activations