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

    Neuronpedia

    INDEX
    Explanations

    numbers and treatment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DIAG
    1.38
     Thackeray
    1.33
    컨
    1.31
    グ
    1.25
     chronology
    1.23
     cocktails
    1.22
    ギャ
    1.22
     Cong
    1.22
     corrector
    1.20
    cor
    1.19
    POSITIVE LOGITS
    5
    1.74
    6
    1.06
    7
    0.93
    ৫
    0.93
    ۵
    0.91
    ५
    0.89
    Fifty
    0.88
    ₅
    0.87
    ⁵
    0.86
    ٥
    0.86
    Act Density 0.226%

    No Known Activations