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

    Neuronpedia

    INDEX
    Explanations

    diversity and variety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ",
    0.46
    活动
    0.46
    lebnis
    0.45
    mr
    0.45
     攵
    0.44
     Node
    0.44
    结点
    0.44
    jeto
    0.43
    事件
    0.43
     বৃত্ত
    0.43
    POSITIVE LOGITS
     guise
    0.49
    ное
    0.47
     substantially
    0.46
    IZE
    0.45
     diversidad
    0.44
     weekly
    0.44
     homestead
    0.44
    ージ
    0.43
    astal
    0.43
     disenfranch
    0.43
    Act Density 0.002%

    No Known Activations