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

    Neuronpedia

    INDEX
    Explanations

    predictive analysis and detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    烜
    0.48
    োপাধ্যা
    0.42
    罗马
    0.42
    mazione
    0.42
    耶路撒
    0.42
     Perkenalkan
    0.41
    旋转
    0.40
    اء
    0.40
    ází
    0.40
    ེ
    0.40
    POSITIVE LOGITS
     predict
    1.00
     predicting
    1.00
     predictive
    0.99
     prediction
    0.90
     predicts
    0.88
     Predictive
    0.85
    预测
    0.84
    predict
    0.84
     Predicting
    0.83
     detecting
    0.82
    Act Density 0.115%

    No Known Activations