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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unapolog
    0.40
    基础设施
    0.39
    çar
    0.38
    форд
    0.38
    ประมาณ
    0.37
     regalías
    0.37
    acariy
    0.36
    自动化
    0.36
    འི་
    0.36
    财政
    0.36
    POSITIVE LOGITS
    ↵
    0.49
     \
    0.48
    0.41
     \\
    0.37
     //
    0.37
    ]
    0.35
     OL
    0.34
     \}
    0.34
     {\
    0.33
     catastrophic
    0.32
    Act Density 0.099%

    No Known Activations