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

    Neuronpedia

    INDEX
    Explanations

    scientific experiment and demonstration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Translation
    0.88
    翻訳
    0.81
    translation
    0.80
     Translation
    0.80
     நிறுவன
    0.80
     traducción
    0.78
     अनुवाद
    0.78
     translation
    0.78
    翻譯
    0.76
    ranos
    0.76
    POSITIVE LOGITS
     experiments
    1.91
     Experiments
    1.85
     experiment
    1.83
     실험
    1.74
    実験
    1.71
    Experiments
    1.71
     Experiment
    1.68
    experiments
    1.64
     experimento
    1.61
    Experiment
    1.60
    Act Density 0.181%

    No Known Activations