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

    Neuronpedia

    INDEX
    Explanations

    the followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    の世界
    0.24
    独
    0.23
    🏞
    0.22
    世界
    0.22
    renowned
    0.22
    避免
    0.22
    慎
    0.22
    വി
    0.21
    生产
    0.21
    🌍
    0.21
    POSITIVE LOGITS
     offending
    0.21
     bereits
    0.21
     first
    0.21
     cartridge
    0.21
     entsprechende
    0.20
     defendant
    0.20
     instance
    0.19
    ].
    0.19
     proteinuria
    0.19
    ].[
    0.19
    Act Density 0.066%

    No Known Activations