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

    Neuronpedia

    INDEX
    Explanations

    spraying, project, patient, everyone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     northern
    0.48
    \
    0.46
    ]
    0.46
     southern
    0.45
    國家
    0.43
     ۾
    0.42
     boats
    0.41
    बा
    0.41
    幢
    0.40
     tourism
    0.39
    POSITIVE LOGITS
    tend
    0.52
     назвал
    0.50
    さら
    0.50
     экстра
    0.48
     Tend
    0.47
     улуч
    0.45
     Crunch
    0.45
    фии
    0.45
     сохра
    0.45
     உட்பட
    0.45
    Act Density 0.002%

    No Known Activations