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

    Neuronpedia

    INDEX
    Explanations

    Spring Cloud

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     O
    0.43
    бора
    0.40
     بوتل
    0.38
    Ｏ
    0.38
    ()-
    0.36
    zaXRvcn
    0.36
    Zona
    0.35
     Op
    0.35
     Ole
    0.35
    Tra
    0.35
    POSITIVE LOGITS
    package
    0.41
     jesus
    0.41
     جعفر
    0.40
    嵇
    0.40
     Glut
    0.39
     joseph
    0.39
     jane
    0.38
     james
    0.38
     rad
    0.38
     richard
    0.38
    Act Density 0.000%

    No Known Activations