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

    Neuronpedia

    INDEX
    Explanations

    less impatient, already grilling, decomposes upon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     차
    0.48
    टी
    0.45
     வெற்ற
    0.45
    내
    0.43
    車の
    0.43
    ટી
    0.43
    Formerly
    0.42
    됐
    0.42
    Tiles
    0.42
    대전
    0.42
    POSITIVE LOGITS
     ADAM
    0.45
    erade
    0.41
     lingu
    0.40
    b
    0.40
    EME
    0.39
    ಗ್ಗ
    0.39
     identity
    0.39
     ethanol
    0.39
     andra
    0.39
     fogy
    0.39
    Act Density 0.004%

    No Known Activations