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

    Neuronpedia

    INDEX
    Explanations

    区别 and other concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ปลี่ยน
    0.40
    తంగా
    0.40
    变革
    0.39
    никами
    0.38
    邓
    0.38
     посредством
    0.37
    撗
    0.37
    当該
    0.37
     റ
    0.36
    捛
    0.36
    POSITIVE LOGITS
    也是
    0.71
     rất
    0.70
     undoubtedly
    0.70
     very
    0.66
    无疑
    0.66
    都是
    0.66
     ძალიან
    0.64
     definitely
    0.63
     indeed
    0.63
     είναι
    0.63
    Act Density 0.001%

    No Known Activations