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

    Neuronpedia

    INDEX
    Explanations

    closing parentheses and code statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     khususnya
    0.91
     particularly
    0.86
    especially
    0.85
    particularly
    0.84
    Especially
    0.82
    특히
    0.81
     인터넷
    0.80
     especially
    0.78
     중심으로
    0.78
     besonders
    0.77
    POSITIVE LOGITS
    ↵
    0.97
    ↵↵
    0.92
    ignés
    0.90
     Если
    0.82
    籶
    0.81
     Фі
    0.80
    uées
    0.79
    abia
    0.76
    ignées
    0.75
    ực
    0.75
    Act Density 0.516%

    No Known Activations